Kagan Tumer's Publications

Display Publications by [Year] [Type] [Topic]


Multi-objective Neuro-evolutionary Control for a Fuel Cell Turbine Hybrid Energy System. M. Colby, L. Yliniemi, P. Pezzini, D. Tucker, K.M. Bryden, and K. Tumer. In Proceedings of Genetic and Evolutionary Computation Conference (GECCO), pp. 877–864, Denver, CO, July 2016.

Abstract

Increased energy demands are driving the development of new power generation technologies with high efficient. Direct fired fuel cell turbine hybrid systems are one such development, which have the potential to dramatically increase power generation efficiency, quickly respond to transient loads, and offer fast start up times. However, traditional control techniques are often inadequate in these systems because of extremely high nonlinearities and coupling between system parameters. In this work, we develop multi-objective neural network controller via neuro-evolution and the Pareto Concavity Elimination Transformation (PaCcET). In order for the training process to be computationally tractable, we develop a computationally efficient plant simulator based on physical plant data, allowing for rapid fitness assignment. Results demonstrate that the multi-objective algorithm is able to develop a Pareto front of control policies which represent tradeoffs between tracking desired turbine speed profiles and minimizing transient operation of the fuel cell.

Download

(unavailable)

BibTeX Entry

@InProceedings{tumer-colby_gecco16,
author = {M. Colby and  L. Yliniemi and P. Pezzini and D. Tucker and K.M. Bryden and K. Tumer},
title = {Multi-objective Neuro-evolutionary Control for a Fuel Cell Turbine Hybrid Energy System},
booktitle = {Proceedings of Genetic and Evolutionary Computation Conference (GECCO)},
address = {Denver, CO},
month = {July},
 pages={},
 abstract={Increased energy demands are driving the development of new power generation technologies with high efficient.  Direct fired fuel cell turbine hybrid systems are one such development, which have the potential to dramatically increase power generation efficiency, quickly respond to transient loads, and offer fast start up times.  However, traditional control techniques are often inadequate in these systems because of extremely high nonlinearities and coupling between system parameters.  In this work, we develop multi-objective neural network controller via neuro-evolution and the Pareto Concavity Elimination Transformation (PaCcET).  In order for the training process to be computationally tractable, we develop a computationally efficient plant simulator based on physical plant data, allowing for rapid fitness assignment.  Results demonstrate that the multi-objective algorithm is able to develop a Pareto front of control policies which represent tradeoffs between tracking desired turbine speed profiles and minimizing transient operation of the fuel cell.},
 pages={877-864},
	bib2html_pubtype = {Refereed Conference Papers},
	bib2html_rescat = {Optimization},
year = {2016}
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43