skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Expanding the power of expert systems applications with neural networks

Abstract

It is well known that expert systems are useful in capturing expertise and applying knowledge to chemical engineering problems such as diagnosis, process control, process simulation, process advisory, etc. Traditionally, expert system applications are limited to knowledge domains that are heuristic and involve only simple mathematics. Neural networks however, represent an emerging technology capable of rapid recognition of patterned behavior without regard to mathematical complexity. Although useful in problem identification, neural networks are not very efficient in pointing to in-depth solutions and typically do not promote deep understanding of the problem or the reasoning behind its solutions. This paper explores the potential for expanding the scope of expert system applications by combining expert systems and neural networks. Specifically, this work demonstrates the use of knowledge that is pattern driven rather than heuristic and may be fuzzy, which is characteristic of many problems in chemical engineering. The feasibility of combining these two artificial intelligence (AI) technologies is explored through chemical engineering unit operations examples.

Authors:
;  [1];  [2]
  1. Oak Ridge National Lab., TN (USA)
  2. Naval Academy, Annapolis, MD (USA)
Publication Date:
Research Org.:
Oak Ridge National Lab., TN (USA)
Sponsoring Org.:
DOE/ER
OSTI Identifier:
6680668
Report Number(s):
CONF-900828-6
ON: DE90016032
DOE Contract Number:  
AC05-84OR21400
Resource Type:
Conference
Resource Relation:
Conference: Summer national meeting of the American Institute of Chemical Engineers, San Diego, CA (USA), 19-22 Aug 1990
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; EXPERT SYSTEMS; NEURAL NETWORKS; ARTIFICIAL INTELLIGENCE; LEARNING; USES; 990200* - Mathematics & Computers

Citation Formats

Ferrada, J J, Osborne-Lee, I W, and Cuccuzzella, N. Expanding the power of expert systems applications with neural networks. United States: N. p., 1990. Web.
Ferrada, J J, Osborne-Lee, I W, & Cuccuzzella, N. Expanding the power of expert systems applications with neural networks. United States.
Ferrada, J J, Osborne-Lee, I W, and Cuccuzzella, N. Mon . "Expanding the power of expert systems applications with neural networks". United States.
@article{osti_6680668,
title = {Expanding the power of expert systems applications with neural networks},
author = {Ferrada, J J and Osborne-Lee, I W and Cuccuzzella, N},
abstractNote = {It is well known that expert systems are useful in capturing expertise and applying knowledge to chemical engineering problems such as diagnosis, process control, process simulation, process advisory, etc. Traditionally, expert system applications are limited to knowledge domains that are heuristic and involve only simple mathematics. Neural networks however, represent an emerging technology capable of rapid recognition of patterned behavior without regard to mathematical complexity. Although useful in problem identification, neural networks are not very efficient in pointing to in-depth solutions and typically do not promote deep understanding of the problem or the reasoning behind its solutions. This paper explores the potential for expanding the scope of expert system applications by combining expert systems and neural networks. Specifically, this work demonstrates the use of knowledge that is pattern driven rather than heuristic and may be fuzzy, which is characteristic of many problems in chemical engineering. The feasibility of combining these two artificial intelligence (AI) technologies is explored through chemical engineering unit operations examples.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {1990},
month = {1}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: