The use of the neuro-dynamic programming method for real-time control of a parallel hybrid electric vehicle is addressed in this study. The validated model of a research prototype parallel hybrid electric light commercial vehicle, FOHEV I, is used in the numerical parts of this paper. A diesel engine and an electric motor power the front and rear axles, respectively. Due to the computational complexity and resulting burden for optimum power distribution in the hybrid electric powertrain, real-time computation using dynamic programming is not feasible. Sub-optimal optimization techniques are available for pre-defined speed profiles, however, the vehicle speed profile depends on the driver input and vehicle and road conditions and is not known a priori. A neuro-dynamic programming method is proposed here to solve this problem. The results are compared with and found to be quite close to the optimal ones computed using dynamic programming.
Copyright 2010 IEEE. Reprinted from 2010 IEEE International Conference on Systems Man and Cybernetics : proceedings : 10-13 October 2010, Istanbul, Turkey. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Macquarie University’s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to firstname.lastname@example.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.