Neural network based power management of hydraulic hybrid vehicles

Authors

  • Michael Sprengel Maha Fluid Power Research Center, Purdue University, West Lafayette, IN, USA http://orcid.org/0000-0002-8556-6999
  • Monika Ivantysynova Maha Fluid Power Research Center, Purdue University, West Lafayette, IN, USA

DOI:

https://doi.org/10.1080/14399776.2016.1232117

Keywords:

dynamic programming, neural network, power management, Hydraulic hybrid

Abstract

Effective power management is key to maximizing the performance and efficiency of hydraulic hybrid powertrains. However, the strong influence of future driving events on the optimal control policy limits the effectiveness of many approaches investigated to date. To address this issue the authors have proposed and investigated a novel power management controller that aims to predict online the accumulator’s near optimal state trajectory. It is demonstrated in this paper that if the optimal accumulator state trajectory is known, then an implementable control scheme can achieve near globally optimal fuel efficiency. Controller development began by optimally controlling a series hybrid over a representative drive cycle using Dynamic Programming (DP). A Neural Network (NN) was then trained to reproduce the DP optimal accumulator pressure trajectory based on the vehicle’s velocity over the previous thirty seconds. In this way the NN generalized the relationship between vehicle velocity and accumulator pressure. The NN power management controller’s performance was then evaluated on a hardware-in-the-loop transmission dynamometer using untrained drive cycles to demonstrate the generality of the proposed approach. During these untrained evaluation cycles the NN controller was able to decrease average fuel consumption by 25.8% when compared to a baseline constant pressure control strategy.

Downloads

Download data is not yet available.

Author Biographies

Michael Sprengel, Maha Fluid Power Research Center, Purdue University, West Lafayette, IN, USA

Michael Sprengel was born on 13 May 1987 in Cape Girardeau, Missouri (USA). He received his BS in Mechanical Engineering at the Missouri University of Science and Technology in 2010, his MS in Mechanical Engineering from Purdue University in 2013, and his PhD in Engineering from Purdue University in 2015. Currently he, is employed as an R&D engineer/analyst at Czero in Fort Collins, CO. His research interests include the design, simulation, control, and optimization of novel energy efficient hydraulic hybrid systems for on-road and off-highway applications.

Monika Ivantysynova, Maha Fluid Power Research Center, Purdue University, West Lafayette, IN, USA

Monika Ivantysynova was born on 11 December 1955 in Polenz (Germany). She received her MSc degree in Mechanical Engineering and her PhD degree in Fluid Power from the Slovak Technical University of Bratislava, Czechoslovakia. After 7 years in fluid power industry she returned to university. In April 1996 she received a Professorship in fluid power & control at the University of Duisburg (Germany). From 1999 until August 2004 she was Professor of Mechatronic Systems at the Technical University of Hamburg-Harburg. Since August 2004 she is Professor at Purdue University, USA. Her main research areas are energy saving actuator technology and model based optimization of displacement machines as well as modelling, simulation and testing of fluid power systems. Besides the book ‘Hydrostatic Pumps and Motors’ published in German and English, she has published more than 80 papers in technical journals and at international conferences.

References

Argonne National Laboratory, 2015. PSAT (powertrain

systems analysis toolkit). Available from: www.

transportation.anl.gov.

Bellman, R., 1956. Dynamic programming and lagrange

multipliers. Proceedings of the national academy of sciences

of the United States of America, 42 (10), 767–769.

Bertsekas, D. and Bertsekas, D., 1995. Dynamic programming

and optimal control. vol 1. Belmont, MA: Athena Scientific.

Buchwald, P., et al., 1979. Improvement of a citybus fuel

economy using a hydraulic hybrid propulsion system –

a theoretical and experimental study. Proceedings of the

automotive engineering congress and exposition, 26

February–2 March 1979, Detroit, MI, USA. SAE paper

Environmental Protection Agency (EPA), 2015. Available

from: http://www3.epa.gov/nvfel/testing/dynamometer.

htm.

Heskitt, M., Smith, T., and Hopkins, J., 2012. Design &

development of the LCO-140H series hydraulic hybrid

low floor transit bus: BUSolutions final technical report

(No. FTA Report No. 0018). US Federal Transportation

Authority Report. Available from: http://ntl.bts.gov/

lib/55000/55500/55504/FTA_Report_No._0018.pdf

Johansson, A. and Ossyra, J.-C., 2010. Hydraulic hybrid

transmission design considerations for optimal customer

satisfaction. Proceedings of the 7th international fluid power

conference, 22–24 March 2010 Aachen, Germany.

Johri, R., Baseley, S., and Filipi, Z., 2011. Simultaneous

optimization of supervisory control and gear shift logic

for a parallel hydraulic hybrid refuse truck using stochastic

dynamic programming. ASME/bath symposium on fluid

power and motion control, Arlington, VI, USA.

Kim, Y. and Filipi, Z., 2007. Series hydraulic hybrid

propulsion for a light truck-optimizing the thermostatic

power management. In: Proceedings of the 8th International

Conference on Engines for Automobile, 16–20 September

Capri, Italy. SAE technical paper 2007-24-0080.

Kumar, R. and Ivantysynova, M., 2010. Investigation of

various power management strategies for a class of

hydraulic hybrid powertrains: theory and experiments.

Proceedings of the 6th FPNI PhD symposium, 15–19 June

West Lafayette, IN, USA.

Liu, J. and Peng, H., 2006. Control optimization for a powersplit

hybrid vehicle. American control conference, 14–16

June 2006 Minneapolis, MN, USA. IEEE.

Mikeska, D. and Ivantysynova, M., 2002. A precise steadystate

model of displacement machines for the application

in virtual prototyping of power-split drives. Proceedings of

the 2nd FPNI PhD symposium, 3–6 July 2002 Modena, Italy.

Moré, J., 1978. The Levenberg-Marquardt algorithm:

implementation and theory. In: Numerical analysis. Berlin

Heidelberg: Springer, 105–116.

Musardo, C., et al., 2005. A-ECMS: an adaptive algorithm

for hybrid electric vehicle energy management. European

journal of control, 11 (4), 509–524.

Pourmovahed, A., et al., 1988. Experimental evaluation

of hydraulic accumulator efficiency with and without

elastomeric foam. Journal of propulsion and power, 4 (2),

–192.

PSA-Peugeot-Citroen, 2015. Hybrid air, an innovative full

hybrid gasoline system. Available from: http://www.psapeugeot-

citroen.com.

Sprengel, M. and Ivantysynova, M. 2013. Investigation and

energetic analysis of a novel hydraulic hybrid architecture

for on-road vehicles. Proceedings of the 13th scandinavian

international conference on fluid power, 3–5 June 2013

Linkoping, Sweden.

Sprengel, M. and Ivantysynova, M., 2014. Hardware-inthe-

loop testing of a novel blended hydraulic hybrid

transmission. Proceedings of the 8th FPNI PhD symposium

on fluid power, 11–13 June 2014 Lappeenranta, Finland.

Wendel, G., et al., 2007. Hydraulic hybrid vehicle system

panel. Michigan clean fleet conference, 17 May 2007

Detroit, MI, USA.

Wu, B., et al., 2004. Optimal power management for a

hydraulic hybrid delivery truck. Vehicle system dynamics,

(1–2), 23–40.

Downloads

Published

2017-08-01

How to Cite

Sprengel, M., & Ivantysynova, M. (2017). Neural network based power management of hydraulic hybrid vehicles. International Journal of Fluid Power, 18(2), 79–91. https://doi.org/10.1080/14399776.2016.1232117

Issue

Section

Original Article

Most read articles by the same author(s)

1 2 > >>