Cam-phasing is increasingly considered as a feasible Variable Valve Timing (VVT) technology for production engines. Additional independent control variables in a dual-independent VVT engine increase the complexity of the system, and achieving its full benefit depends critically on devising an optimum control strategy. A traditional approach relying on hardware experiments to generate set-point maps for all independent control variables leads to an exponential increase in the number of required tests and prohibitive cost. Instead, this work formulates the task of defining actuator set-points as an optimization problem. In our previous study, an optimization framework was developed and demonstrated with the objective of maximizing torque at full load. This study extends the technique and uses the optimization framework to minimize fuel consumption of a VVT engine at part load. By adding a penalty term for NOx emissions in the optimization objective, the tradeoff of fuel consumption and NOx emissions is explored. The methodology relies on high-fidelity simulations for pre-optimality studies and as means of generating data that characterize engine behavior in the multi-dimensional space. Artificial Neural Networks (ANN) are then trained on sets of high-fidelity simulation data and used as surrogate models, thus enabling optimization runs requiring hundreds of function evaluations. A case study performed for a DaimlerChrysler 2.4 liter four-cylinder SI engine demonstrates the use of the algorithm for minimizing fuel consumption while simultaneously meeting NOx emission targets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Cam-phasing Optimization Using Artificial Neural Networks as Surrogate Models-Fuel Consumption and NOx Emissions


    Weitere Titelangaben:

    Sae Technical Papers


    Beteiligte:
    Wu, Bin (Autor:in) / Kramer, Denise M. (Autor:in) / Ohl, Gregory L. (Autor:in) / Prucka, Robert G. (Autor:in) / Filipi, Zoran (Autor:in)

    Kongress:

    SAE 2006 World Congress & Exhibition ; 2006



    Erscheinungsdatum :

    2006-04-03




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch





    2006-01-1512 Cam-phasing Optimization Using Artificial Neural Networks as Surrogate Models-Fuel Consumption and NOx Emissions

    Wu, B. / Prucka, R.G. / Filipi, Z.S. et al. | British Library Conference Proceedings | 2006


    Cam-Phasing Optimization Using Artificial Neural Networks as Surrogate Models-Maximizing Torque Output

    Wu, Bin / Kramer, Denise M. / Ohl, Gregory L. et al. | SAE Technical Papers | 2005



    Using Artificial Neural Networks for Predicting Ship Fuel Consumption

    Nguyen Van Giao / Rajamohan Sakthivel / Rudzki Krzysztof et al. | DOAJ | 2023

    Freier Zugriff