By Topic

Model Predictive Control for PEMFC Based on Least Square Support Vector Machine

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Jun Lu ; Electr. & Comput. Eng., James Cook Univ., Townsville, QLD, Australia ; Zahedi, A.

The modelling and control of PEMFC possesses great challenges due to PEMFC system's inherent nonlinearities and time-varying characteristics. The objective of this paper is to propose a novel model predictive control (MPC) strategy based on the least square support vector machine (LSSVM). First, a set of LSSVM models are generated and each model represents one PEMFC performance output. By mapping PEMFC performance outputs as a function of various operation conditions, LSSVM models disregard complex internal details and thus provide low calculation burden for the control algorithm. Then model predictive control is employed by using Model Predictive Control Toolbox in the MATLAB/SIMULINK environment. The LSSVM model and the model predictive controller are simulated and the results demonstrate their effectiveness. The nominal value of the oxygen excess ratio and the stack voltage are able to be maintained during abrupt changes in the stack current.

Published in:

Power and Energy Engineering Conference (APPEEC), 2012 Asia-Pacific

Date of Conference:

27-29 March 2012