Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle

Wai Kean Yap, Vishy Karri, Tien Ho

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    This paper presents an alternative tool for vehicle tuning applications by incorporating the use of artificial neural network (ANN) virtual sensors for a hydrogen-powered car. The objective of this study is to optimize simple engine process parameters to regulate the exhaust emissions. The engine process parameters (throttle position, lambda, ignition advance and injection angle) and the exhaust emission variables (CO, CO 2, HC and NO x) form the basis of the virtual sensors. Experimental data were first obtained through a comprehensive experimental and tuning procedure for neural network training and validation. The optimization layer-by-layer neural network was used to construct two ANN virtual sensors; the engine and emissions models. The performance and accuracy of the proposed virtual sensors were found to be acceptable with the maximum predictive mean relative errors of 0.65%. With its accurate predictive capability, the virtual sensors were then employed and simulated as a measurement tool for vehicle tuning and optimization. Simulation results showed that the exhaust emissions can be regulated by optimizing simple engine process parameters. This study presents an alternative tool for vehicle tuning applications for a hydrogen-powered vehicle. In addition, this work also provided a tool to better understand the effects of various engine conditions on the exhaust emissions without the need for any vehicle modifications.
    Original languageEnglish
    Pages (from-to)8704-8715
    Number of pages12
    JournalInternational Journal of Hydrogen Energy
    Volume37
    Issue number10
    DOIs
    Publication statusPublished - May 2012

    Fingerprint

    exhaust emission
    Emission control
    engines
    vehicles
    Engines
    Neural networks
    Hydrogen
    Tuning
    optimization
    tuning
    sensors
    Sensors
    hydrogen
    ignition
    Ignition
    education
    Railroad cars
    injection
    simulation

    Cite this

    @article{fc76e7fc48ee4fbd8b122e8a6d388551,
    title = "Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle",
    abstract = "This paper presents an alternative tool for vehicle tuning applications by incorporating the use of artificial neural network (ANN) virtual sensors for a hydrogen-powered car. The objective of this study is to optimize simple engine process parameters to regulate the exhaust emissions. The engine process parameters (throttle position, lambda, ignition advance and injection angle) and the exhaust emission variables (CO, CO 2, HC and NO x) form the basis of the virtual sensors. Experimental data were first obtained through a comprehensive experimental and tuning procedure for neural network training and validation. The optimization layer-by-layer neural network was used to construct two ANN virtual sensors; the engine and emissions models. The performance and accuracy of the proposed virtual sensors were found to be acceptable with the maximum predictive mean relative errors of 0.65{\%}. With its accurate predictive capability, the virtual sensors were then employed and simulated as a measurement tool for vehicle tuning and optimization. Simulation results showed that the exhaust emissions can be regulated by optimizing simple engine process parameters. This study presents an alternative tool for vehicle tuning applications for a hydrogen-powered vehicle. In addition, this work also provided a tool to better understand the effects of various engine conditions on the exhaust emissions without the need for any vehicle modifications.",
    keywords = "Emissions model, Engine conditions, Engine parameter, Exhaust emission, Exhaust emissions control, Experimental data, Hydrogen powered vehicles, Hydrogen vehicles, Ignition advance, Injection angles, Layer-by-layers, Mean relative error, Measurement tools, Neural network training, Predictive capabilities, Predictive modelling, Process parameters, Tuning and optimization, Vehicle modifications, Virtual sensor, Carbon dioxide, Engines, Hydrogen, Neural networks, Optimization, Vehicles, Sensors",
    author = "Yap, {Wai Kean} and Vishy Karri and Tien Ho",
    year = "2012",
    month = "5",
    doi = "10.1016/j.ijhydene.2012.02.153",
    language = "English",
    volume = "37",
    pages = "8704--8715",
    journal = "International Journal of Hydrogen Energy",
    issn = "0360-3199",
    publisher = "Elsevier",
    number = "10",

    }

    Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle. / Yap, Wai Kean; Karri, Vishy; Ho, Tien.

    In: International Journal of Hydrogen Energy, Vol. 37, No. 10, 05.2012, p. 8704-8715.

    Research output: Contribution to journalArticleResearchpeer-review

    TY - JOUR

    T1 - Exhaust emissions control and engine parameters optimization using artificial neural network virtual sensors for a hydrogen-powered vehicle

    AU - Yap, Wai Kean

    AU - Karri, Vishy

    AU - Ho, Tien

    PY - 2012/5

    Y1 - 2012/5

    N2 - This paper presents an alternative tool for vehicle tuning applications by incorporating the use of artificial neural network (ANN) virtual sensors for a hydrogen-powered car. The objective of this study is to optimize simple engine process parameters to regulate the exhaust emissions. The engine process parameters (throttle position, lambda, ignition advance and injection angle) and the exhaust emission variables (CO, CO 2, HC and NO x) form the basis of the virtual sensors. Experimental data were first obtained through a comprehensive experimental and tuning procedure for neural network training and validation. The optimization layer-by-layer neural network was used to construct two ANN virtual sensors; the engine and emissions models. The performance and accuracy of the proposed virtual sensors were found to be acceptable with the maximum predictive mean relative errors of 0.65%. With its accurate predictive capability, the virtual sensors were then employed and simulated as a measurement tool for vehicle tuning and optimization. Simulation results showed that the exhaust emissions can be regulated by optimizing simple engine process parameters. This study presents an alternative tool for vehicle tuning applications for a hydrogen-powered vehicle. In addition, this work also provided a tool to better understand the effects of various engine conditions on the exhaust emissions without the need for any vehicle modifications.

    AB - This paper presents an alternative tool for vehicle tuning applications by incorporating the use of artificial neural network (ANN) virtual sensors for a hydrogen-powered car. The objective of this study is to optimize simple engine process parameters to regulate the exhaust emissions. The engine process parameters (throttle position, lambda, ignition advance and injection angle) and the exhaust emission variables (CO, CO 2, HC and NO x) form the basis of the virtual sensors. Experimental data were first obtained through a comprehensive experimental and tuning procedure for neural network training and validation. The optimization layer-by-layer neural network was used to construct two ANN virtual sensors; the engine and emissions models. The performance and accuracy of the proposed virtual sensors were found to be acceptable with the maximum predictive mean relative errors of 0.65%. With its accurate predictive capability, the virtual sensors were then employed and simulated as a measurement tool for vehicle tuning and optimization. Simulation results showed that the exhaust emissions can be regulated by optimizing simple engine process parameters. This study presents an alternative tool for vehicle tuning applications for a hydrogen-powered vehicle. In addition, this work also provided a tool to better understand the effects of various engine conditions on the exhaust emissions without the need for any vehicle modifications.

    KW - Emissions model

    KW - Engine conditions

    KW - Engine parameter

    KW - Exhaust emission

    KW - Exhaust emissions control

    KW - Experimental data

    KW - Hydrogen powered vehicles

    KW - Hydrogen vehicles

    KW - Ignition advance

    KW - Injection angles

    KW - Layer-by-layers

    KW - Mean relative error

    KW - Measurement tools

    KW - Neural network training

    KW - Predictive capabilities

    KW - Predictive modelling

    KW - Process parameters

    KW - Tuning and optimization

    KW - Vehicle modifications

    KW - Virtual sensor

    KW - Carbon dioxide

    KW - Engines

    KW - Hydrogen

    KW - Neural networks

    KW - Optimization

    KW - Vehicles

    KW - Sensors

    U2 - 10.1016/j.ijhydene.2012.02.153

    DO - 10.1016/j.ijhydene.2012.02.153

    M3 - Article

    VL - 37

    SP - 8704

    EP - 8715

    JO - International Journal of Hydrogen Energy

    JF - International Journal of Hydrogen Energy

    SN - 0360-3199

    IS - 10

    ER -