This paper presents a sensitivity-based input selection algorithm and a layered modeling approach for improving Gaussian Process Regression (GPR) modeling with hyperparameter optimization for engine model development with data sets of 120 training points or less. The models presented here are developed for a Pilot-Ignited Direct-Injected Natural Gas (PIDING) engine. A previously developed GPR modeling method with hyperparameter optimization produced some models with normalized root mean square error (nRMSE) over 0.2. The input selection method reduced the overall error by 0.6% to 18.85% while the layered modeling method improved the error for carbon monoxide (CO) by 52.6%, particulate matter (PM) by 32.5%, and nitrogen oxides (NOX) by 29.8%. These results demonstrate the importance of selecting only the most relevant inputs for machine learning models. This also shows that a layered approach to modeling could be implemented to further refine the inputs and provide a reduction in machine learning modeling error.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Refinement of Gaussian Process Regression Modeling of Pilot-Ignited Direct-Injected Natural Gas Engines


    Additional title:

    Sae Technical Papers


    Contributors:

    Conference:

    Automotive Technical Papers ; 2022



    Publication date :

    2022-09-23




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Optimization study of pilot-ignited natural gas direct-injection in diesel engines

    Li,G. / Quellette,P. / Dumitrescu,S. et al. | Automotive engineering | 1999


    Optimization Study of Pilot-Ignited Natural Gas Direct-Injection in Diesel Engines

    Li, Guowei / Ouellette, Patric / Hill, Philip G. et al. | SAE Technical Papers | 1999


    Injection Parameter Effects on a Direct Injected, Pilot Ignited, Heavy Duty Natural Gas Engine with EGR

    McTaggart-Cowan, G. P. / Hill, P. G. / Rogak, S. N. et al. | SAE Technical Papers | 2003


    Injection Parameter Effects on a Direct Injected, Pilot Ignited, Heavy Duty Natural Gas Engine with EGR

    McTaggart-Cowan, G. P. / Bushe, W. K. / Rogak, S. N. et al. | British Library Conference Proceedings | 2003


    Injection parameters effects on a direct injected, pilot ignited, heavy duty natural gas engine with EGR

    MCTaggart-Cowan,G.P. / Bushe,W.K. / Rogak,S.N. et al. | Automotive engineering | 2003