It has been demonstrated in the previous research that the node connectivity in the graph encoding the topological neighborhood relationships between local models in a piecewise dynamic model may significantly affect the cooperative learning process. It was shown that a graph with a larger connectivity leads to a quicker learning adaption due to more rapidly decaying transients of the estimation of local model parameters. In the same time, it was shown that the accuracy could be degraded by a larger bias in the asymptotic portion of the estimations of local model parameters. The efforts in topology optimization should therefore strive towards a high accuracy of the asymptotic portion of the estimator of local model parameters while simultaneously accelerating the decay of the estimation transients. In this paper, we pursue minimization of the residual sum of squares of a piecewise dynamic model after a predetermined number of training steps. The optimization of inter-model topology is implemented via a genetic algorithm that manipulates adjacency matrices of the graph underlying the piecewise dynamic model. An example of applying the topology optimization procedure on a peicewise linear model of a highly nonlinear dynamic system is provided to show the efficacy of the new method.
Skip Nav Destination
ASME 2010 Dynamic Systems and Control Conference
September 12–15, 2010
Cambridge, Massachusetts, USA
Conference Sponsors:
- Dynamic Systems and Control Division
ISBN:
978-0-7918-4418-2
PROCEEDINGS PAPER
Topology Optimization for Piecewise Dynamic Models Using a Genetic Algorithm Available to Purchase
Dragan Djurdjanovic
Dragan Djurdjanovic
University of Texas at Austin, Austin, TX
Search for other works by this author on:
Yi Liu
University of Texas at Austin, Austin, TX
Dragan Djurdjanovic
University of Texas at Austin, Austin, TX
Paper No:
DSCC2010-4180, pp. 421-429; 9 pages
Published Online:
January 25, 2011
Citation
Liu, Y, & Djurdjanovic, D. "Topology Optimization for Piecewise Dynamic Models Using a Genetic Algorithm." Proceedings of the ASME 2010 Dynamic Systems and Control Conference. ASME 2010 Dynamic Systems and Control Conference, Volume 2. Cambridge, Massachusetts, USA. September 12–15, 2010. pp. 421-429. ASME. https://doi.org/10.1115/DSCC2010-4180
Download citation file:
8
Views
Related Proceedings Papers
Related Articles
Topology Optimization of Large Motion Rigid Body Mechanisms With Nonlinear Kinematics
J. Comput. Nonlinear Dynam (April,2009)
Design of 2-DOF Compliant Mechanisms to Form Grip-and-Move Manipulators for 2D Workspace
J. Mech. Des (March,2010)
Parameters Identification for Nonlinear Dynamic Systems Via Genetic Algorithm Optimization
J. Comput. Nonlinear Dynam (October,2009)
Related Chapters
Multiobjective Genetic Algorithm for Reverse Logistics Network Problem Using Priority-Based Encoding
Intelligent Engineering Systems through Artificial Neural Networks Volume 18
An Approach for System Development Using Evolutionary Probabilistic Strategy and Grammar Rules
Intelligent Engineering Systems through Artificial Neural Networks, Volume 16
Design of Experiments for Model Development and Validation
Nonlinear Regression Modeling for Engineering Applications: Modeling, Model Validation, and Enabling Design of Experiments