The increasing sensing and computational capacities of vehicles enable novel opportunities for optimal control strategies, including powertrain control strategies to improve fuel economy. In this chapter, we present the concept, implementation, and test results for one such strategy, which together represent the culmination of years of research collaboration between academia and industry. Our strategy leverages predictions of acceleration behavior to optimize the dynamic allocation of torque between two sources, the internal combustion engine and the electric motor, for a hybrid electric vehicle. Preliminary development stages included detailed modeling and simulation to demonstrate feasibility and fuel economy improvement potential. Implementation involved the design and fabrication of a test vehicle platform on which the control strategy was installed and actuated. Results of tests using this platform demonstrate an improvement to fuel economy of more than 28% relative to a baseline, non-predictive control strategy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Machine Learning and Optimization Techniques for Automotive Cyber-Physical Systems: Predictive Control During Acceleration Events to Improve Fuel Economy


    Contributors:


    Publication date :

    2023-03-27


    Size :

    22 pages




    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    COMPUTER SIMULATION OF AUTOMOTIVE FUEL ECONOMY AND ACCELERATION

    LUKEY, IVAN / LOUDEN, R. K. | SAE Technical Papers | 1960


    Multicore enablement for automotive cyber physical systems

    Herkersdorf, Andreas / Michel, Hans-Ulrich / Rauchfuss, Holm et al. | Tema Archive | 2012



    Integrating traffic data and model predictive control to improve fuel economy

    Kohut, Nicholas J. / Hedrick, J. Karl / Borrelli, Francesco | Tema Archive | 2009