Application of Random Forest Machine Learning Models to Forecast Combustion Profile Parameters of a Natural Gas Spark Ignition Engine

Predicting internal combustion (IC) engine variables such as the combustion phasing and duration are essential to zero-dimensional (0D) single-zone engine simulations (e.g., for the Wiebe function combustion model). This study investigated the use of a random forest machine learning model to predict these engine combustion parameters as a modality to reduce expensive engine dynamometer tests. A single cylinder four-stroke heavy-duty spark-ignition engine fuelled with methane was operated at different engine speeds and loads to provide the data for training and testing the proposed correlated model. The model inputs were key engine operating variables such as spark timing, mixture equivalence ratio, and engine speed. The performance of the model was validated by comparing the prediction dataset with the experimental results. Results showed that the prediction error of the random forest machine learning algorithm was less than 8%, suggesting that it can be used to predict the combustion profile parameters of interest with acceptable accuracy.

I am repeating the abstract twice because the 400-word minimum is excessive for a preliminary abstract, in my opinion.

Predicting internal combustion (IC) engine variables such as the combustion phasing and duration are essential to zero-dimensional (0D) single-zone engine simulations (e.g., for the Wiebe function combustion model). This study investigated the use of a random forest machine learning model to predict these engine combustion parameters as a modality to reduce expensive engine dynamometer tests. A single cylinder four-stroke heavy-duty spark-ignition engine fuelled with methane was operated at different engine speeds and loads to provide the data for training and testing the proposed correlated model. The model inputs were key engine operating variables such as spark timing, mixture equivalence ratio, and engine speed. The performance of the model was validated by comparing the prediction dataset with the experimental results. Results showed that the prediction error of the random forest machine learning algorithm was less than 8%, suggesting that it can be used to predict the combustion profile parameters of interest with acceptable accuracy.

P

Predicting internal combustion (IC) engine variables such as the combustion phasing and duration are essential to zero-dimensional (0D) single-zone engine simulations (e.g., for the Wiebe function combustion model). This study investigated the use of a random forest machine learning model to predict these engine combustion parameters as a modality to reduce expensive engine dynamometer tests. A single cylinder four-stroke heavy-duty spark-ignition engine fuelled with methane was operated at different engine speeds and loads to provide the data for training and testing the proposed correlated model. The model inputs were key engine operating variables such as spark timing, mixture equivalence ratio, and engine speed. The performance of the model was validated by comparing the prediction dataset with the experimental results. Results showed that the prediction error of the random forest machine learning algorithm was less than 8%, suggesting that it can be used to predict the combustion profile parameters of interest with acceptable accuracy.