Investigation of Heat Transfer Characteristics of Heavy-Duty Spark Ignition Natural Gas Engines Using Machine Learning

Machine learning algorithms are effective tools to reduce the number of engine dynamometer tests during internal combustion engine development and/or optimization. This paper provides a case study of using such a statistical algorithm to characterize the heat transfer from the combustion chamber to the environment during combustion and during the entire engine cycle. The data for building the machine learning model came from a single cylinder compression ignition engine (13.3 compression ratio) that was converted to natural-gas port fuel injection spark-ignition operation. Engine dynamometer tests investigated several spark timings, equivalence ratios, and engine speeds, which were also used as model inputs. While building the model it was found that adding the intake pressure as another model input improved model efficiency. Then, when machine algorithms were compared one to another, an artificial neural network model performed better than a random forest model, especially for operating conditions near the limits of the experimental range. Moreover, the model-assisted analysis indicated that a bowl-in-piston chamber and spark-ignited natural-gas premixed combustion significantly changed the heat transfer characteristics compared to that inside a conventional pent roof combustion chamber. For example, the heat transfer per cycle as a fraction of the fuel’s chemical energy had a maximum for an equivalence ratio between 0.8 and 0.9 in this converted engine, compared to what is seen in traditional gasoline spark ignition engines, where the heat transfer peaks at stoichiometric conditions. Overall, this study’s findings support the use of machine learning algorithms as effective tools to assist in engine development and/or optimization.