TY - GEN
T1 - Pattern matching synthesis as an automated approach to mechanism design
AU - Hoeltzel, D. A.
AU - Chieng, W. H.
N1 - Publisher Copyright:
© 1989 American Society of Mechanical Engineers (ASME). All rights reserved.
PY - 1989
Y1 - 1989
N2 - A new knowledge-based approach for the synthesis of mechanisms, referred to as Pattern Matching Synthesis, has been developed based on committee machine and Hopfield neural network models of pattern matching applied to coupler curves. Computational tests performed on a dimensionally parameterized four bar mechanism have yielded 15 distinct coupler curve groups (patterns) from a total of 356 generated coupler curves. This innovative approach represents a first step toward the automation of mapping structure-Tofunction in mechanism design based on the application of artificial intelligence programming techniques.
AB - A new knowledge-based approach for the synthesis of mechanisms, referred to as Pattern Matching Synthesis, has been developed based on committee machine and Hopfield neural network models of pattern matching applied to coupler curves. Computational tests performed on a dimensionally parameterized four bar mechanism have yielded 15 distinct coupler curve groups (patterns) from a total of 356 generated coupler curves. This innovative approach represents a first step toward the automation of mapping structure-Tofunction in mechanism design based on the application of artificial intelligence programming techniques.
UR - http://www.scopus.com/inward/record.url?scp=85105399918&partnerID=8YFLogxK
U2 - 10.1115/DETC1989-0043
DO - 10.1115/DETC1989-0043
M3 - Conference contribution
AN - SCOPUS:85105399918
T3 - Proceedings of the ASME Design Engineering Technical Conference
SP - 243
EP - 250
BT - Computer-Aided and Computational Design
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 1989 Design Technical Conferences, DETC 1989
Y2 - 17 September 1989 through 21 September 1989
ER -