An integrated architecture for engineering problem-solving

作者: Yusuf Pisan

DOI:

关键词:

摘要: Abstract : Problem solving is an essential function of human cognition. To build intelligent systems that are capable assisting engineers and tutoring students, we need to develop information processing model captures the skills used in engineering problem solving. This thesis describes Integrated Solving Architecture (IPSA) combines qualitative, quantitative diagrammatic reasoning produce annotated solutions problems. We focus on representing expert knowledge, examine how control knowledge provides structure for using domain knowledge. demonstrate our architecture solving, present a Thermodynamics Solver (TPS) uses IPSA architecture. TPS solves over 150 thermodynamics problems taken from first four chapters common textbook produces expert-like solutions.

参考文章(87)
Robert McCartney, Michael Anderson, Diagrammatic reasoning and cases national conference on artificial intelligence. pp. 1004- 1009 ,(1996)
Steven Pinker, A theory of graph comprehension. Lawrence Erlbaum Associates, Inc. ,(1990)
Olivier Raiman, Brian C. Williams, Decompositional modeling through caricatural reasoning national conference on artificial intelligence. pp. 1199- 1204 ,(1994)
Austin Tate, Generating project networks international joint conference on artificial intelligence. pp. 888- 893 ,(1977)
Thomas F. McDougal, Kristian J. Hammond, Representing and using procedural knowledge to build geometry proofs national conference on artificial intelligence. pp. 60- 65 ,(1993)
Shimon Ullman, Visual routines Image understanding 1985-86. pp. 286- 344 ,(1987)
Kenneth D. Forbus, Spatial and qualitative aspects of reasoning about motion national conference on artificial intelligence. pp. 170- 173 ,(1980)
Oren Etzioni, Craig A. Knoblock, Steven Minton, Integrating abstraction and explanation-based learning in PRODIGY national conference on artificial intelligence. pp. 541- 546 ,(1991)