Application of neural networks to fuel processors for fuel cell vehicles

Laura C. Iwan, Robert Frank Stengel

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Passenger vehicles fueled by hydrocarbons or alcohols and powered by proton exchange membrane (PEM) fuel cells address world air quality and fuel supply concerns while avoiding hydrogen infrastructure and on-board storage problems. Reduction of the carbon monoxide concentration in the on-board fuel processor's hydrogen-rich gas by the preferential oxidizer (PrOx) under dynamic conditions is crucial to avoid poisoning of the PEM fuel cell's anode catalyst and thus malfunction of the fuel cell vehicle. A dynamic control scheme is proposed for a single-stage, tubular, cooled PrOx that performs better than, but retains the reliability and ease of use of, conventional industrial controllers. The proposed hybrid control system contains a CMAC artificial neural network in parallel with a conventional PID controller. By using a computer simulation, it was found that the proposed hybrid controller generalizes well to novel driving sequences after being trained on other driving sequences with similar or slower transients. Although it is similar to the PID in terms of software requirements and design effort, the hybrid controller performs significantly better than the PID in terms of H2 conversion setpoint regulation and PrOx outlet CO reduction.

Original languageEnglish (US)
Pages (from-to)1585-1590
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
Volume2
StatePublished - Dec 1 1998
Externally publishedYes

Fingerprint

Fuel Cell
Fuel cells
Neural Networks
Neural networks
Controller
Controllers
Hydrogen
Proton exchange membrane fuel cells (PEMFC)
Carbon Monoxide
Membrane
Hybrid Control
Air Quality
Dynamic Control
PID Controller
Catalyst poisoning
Alcohol
Hydrocarbons
Catalyst
Hybrid Systems
Artificial Neural Network

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Control and Systems Engineering
  • Chemical Health and Safety

Cite this

@article{ca131c0b43e84c9d919e67f397c20ed0,
title = "Application of neural networks to fuel processors for fuel cell vehicles",
abstract = "Passenger vehicles fueled by hydrocarbons or alcohols and powered by proton exchange membrane (PEM) fuel cells address world air quality and fuel supply concerns while avoiding hydrogen infrastructure and on-board storage problems. Reduction of the carbon monoxide concentration in the on-board fuel processor's hydrogen-rich gas by the preferential oxidizer (PrOx) under dynamic conditions is crucial to avoid poisoning of the PEM fuel cell's anode catalyst and thus malfunction of the fuel cell vehicle. A dynamic control scheme is proposed for a single-stage, tubular, cooled PrOx that performs better than, but retains the reliability and ease of use of, conventional industrial controllers. The proposed hybrid control system contains a CMAC artificial neural network in parallel with a conventional PID controller. By using a computer simulation, it was found that the proposed hybrid controller generalizes well to novel driving sequences after being trained on other driving sequences with similar or slower transients. Although it is similar to the PID in terms of software requirements and design effort, the hybrid controller performs significantly better than the PID in terms of H2 conversion setpoint regulation and PrOx outlet CO reduction.",
author = "Iwan, {Laura C.} and Stengel, {Robert Frank}",
year = "1998",
month = "12",
day = "1",
language = "English (US)",
volume = "2",
pages = "1585--1590",
journal = "Proceedings of the IEEE Conference on Decision and Control",
issn = "0191-2216",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Application of neural networks to fuel processors for fuel cell vehicles. / Iwan, Laura C.; Stengel, Robert Frank.

In: Proceedings of the IEEE Conference on Decision and Control, Vol. 2, 01.12.1998, p. 1585-1590.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of neural networks to fuel processors for fuel cell vehicles

AU - Iwan, Laura C.

AU - Stengel, Robert Frank

PY - 1998/12/1

Y1 - 1998/12/1

N2 - Passenger vehicles fueled by hydrocarbons or alcohols and powered by proton exchange membrane (PEM) fuel cells address world air quality and fuel supply concerns while avoiding hydrogen infrastructure and on-board storage problems. Reduction of the carbon monoxide concentration in the on-board fuel processor's hydrogen-rich gas by the preferential oxidizer (PrOx) under dynamic conditions is crucial to avoid poisoning of the PEM fuel cell's anode catalyst and thus malfunction of the fuel cell vehicle. A dynamic control scheme is proposed for a single-stage, tubular, cooled PrOx that performs better than, but retains the reliability and ease of use of, conventional industrial controllers. The proposed hybrid control system contains a CMAC artificial neural network in parallel with a conventional PID controller. By using a computer simulation, it was found that the proposed hybrid controller generalizes well to novel driving sequences after being trained on other driving sequences with similar or slower transients. Although it is similar to the PID in terms of software requirements and design effort, the hybrid controller performs significantly better than the PID in terms of H2 conversion setpoint regulation and PrOx outlet CO reduction.

AB - Passenger vehicles fueled by hydrocarbons or alcohols and powered by proton exchange membrane (PEM) fuel cells address world air quality and fuel supply concerns while avoiding hydrogen infrastructure and on-board storage problems. Reduction of the carbon monoxide concentration in the on-board fuel processor's hydrogen-rich gas by the preferential oxidizer (PrOx) under dynamic conditions is crucial to avoid poisoning of the PEM fuel cell's anode catalyst and thus malfunction of the fuel cell vehicle. A dynamic control scheme is proposed for a single-stage, tubular, cooled PrOx that performs better than, but retains the reliability and ease of use of, conventional industrial controllers. The proposed hybrid control system contains a CMAC artificial neural network in parallel with a conventional PID controller. By using a computer simulation, it was found that the proposed hybrid controller generalizes well to novel driving sequences after being trained on other driving sequences with similar or slower transients. Although it is similar to the PID in terms of software requirements and design effort, the hybrid controller performs significantly better than the PID in terms of H2 conversion setpoint regulation and PrOx outlet CO reduction.

UR - http://www.scopus.com/inward/record.url?scp=0032269944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032269944&partnerID=8YFLogxK

M3 - Article

VL - 2

SP - 1585

EP - 1590

JO - Proceedings of the IEEE Conference on Decision and Control

JF - Proceedings of the IEEE Conference on Decision and Control

SN - 0191-2216

ER -