TY - JOUR
T1 - Knowledge interaction with genetic programming in mechatronic systems design using bond graphs
AU - Wang, Jiachuan
AU - Fan, Zhun
AU - Terpenny, Janis P.
AU - Goodman, Erik D.
N1 - Funding Information:
Manuscript received September 1, 2003; revised February 20, 2004. This work was supported in part by the National Science Foundation under Grants EEC-0332058 and DMII-0084934. This paper was recommended by Guest Editor Y. Jin. J. Wang is with United Technologies Research Center, East Hartford, CT 06108 USA (e-mail: [email protected]). Z. Fan is with the Technical University of Denmark, Lyngby, Denmark (e-mail: [email protected]). J. P. Terpenny is with Virginia Polytechnic Institute and State University, Blacksburg, VA 24061 USA (e-mail: [email protected]). E. D. Goodman is with Michigan State University, East Lansing, MI 48824 USA (e-mail: [email protected]). Digital Object Identifier 10.1109/TSMCC.2004.841915
PY - 2005/5
Y1 - 2005/5
N2 - This paper describes a unified network synthesis approach for the conceptual stage of mechatronic systems design using bond graphs. It facilitates knowledge interaction with evolutionary computation significantly by encoding the structure of a bond graph in a genetic programming tree representation. On the one hand, since bond graphs provide a succinct set of basic design primitives for mechatronic systems modeling, it is possible to extract useful modular design knowledge discovered during the evolutionary process for design creativity and reusability. On the other hand, design knowledge gained from experience can be incorporated into the evolutionary process to improve the topologically open-ended search capability of genetic programming for enhanced search efficiency and design feasibility. This integrated knowledge-based design approach is demonstrated in a quarter-car suspension control system synthesis and a MEMS bandpass filter design application.
AB - This paper describes a unified network synthesis approach for the conceptual stage of mechatronic systems design using bond graphs. It facilitates knowledge interaction with evolutionary computation significantly by encoding the structure of a bond graph in a genetic programming tree representation. On the one hand, since bond graphs provide a succinct set of basic design primitives for mechatronic systems modeling, it is possible to extract useful modular design knowledge discovered during the evolutionary process for design creativity and reusability. On the other hand, design knowledge gained from experience can be incorporated into the evolutionary process to improve the topologically open-ended search capability of genetic programming for enhanced search efficiency and design feasibility. This integrated knowledge-based design approach is demonstrated in a quarter-car suspension control system synthesis and a MEMS bandpass filter design application.
UR - http://www.scopus.com/inward/record.url?scp=18544374721&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=18544374721&partnerID=8YFLogxK
U2 - 10.1109/TSMCC.2004.841915
DO - 10.1109/TSMCC.2004.841915
M3 - Article
AN - SCOPUS:18544374721
SN - 1094-6977
VL - 35
SP - 172
EP - 182
JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
IS - 2
ER -