Comparison of Random Forest and Neural Network in Modeling the Performance and Emissions of a Natural Gas Spark Ignition Engine

Abstract

Machine learning (ML) models can accelerate the development of efficient internal combustion engines. This study assessed the feasibility of data-driven methods towards predicting the performance of a diesel engine modified to natural gas spark ignition, based on a limited number of experiments. As the best ML technique cannot be chosen a priori, the applicability of different ML algorithms for such an engine application was evaluated. Specifically, the performance of two widely used ML algorithms, the random forest (RF) and the artificial neural network (ANN), in forecasting engine responses related to in-cylinder combustion phenomena was compared. The results indicated that both algorithms with spark timing, mixture equivalence ratio, and engine speed as model inputs produced acceptable results with respect to predicting engine performance, combustion phasing, and engine-out emissions. Despite requiring more effort in hyperparameter optimization, the ANN model performed better than the RF model, especially for engine emissions, as evidenced by the larger R-squared, smaller root-mean-square errors, and more realistic predictions of the effects of key engine control variables on the engine performance. However, in applications where the combustion behavior knowledge is limited, it is recommended to use a RF model to quickly determine the appropriate number of model inputs. Consequently, using the RF model to define the model structure and then employing the ANN model to improve the model's predictive capability can help to rapidly build data-driven engine combustion models.

A numerical evaluation and guideline for thermal barrier coatings on gasoline compression ignition engines

“…hotter than metal piston throughout the entire engine cycle) should be avoided for combustion modes that do not require intake thermal management (e.g. boosted SI, 44 MCCI with diesel fuel, gasoline controlled autoignition (CAI) with high internal residual rates, etc.) because charge heating causes difficulties with air handling, lowers power density, and increases the knock tendency (for SI specifically).…”

Forecasting coal power plant retirement ages and lock-in with random forest regression

“…These especially offer greater ease and speed when determining the model structure and during its application and tuning. 64 For energy-related forecasting, Alova et al. 65 used a similar supervised machine-learning technique.…”

Integrating Machine Learning for Predicting Internal Combustion Engine Performance and Segment-Based CO2 Emissions Across Urban and Rural Settings

“…Machine learning offers the capability to adjust input parameters to simulate the combustion characteristics of an engine, thereby forecasting pertinent engine parameters effectively [16], [17]. Intelligent internal combustion engines can analyze a wider array of data inputs, encompassing climate conditions and geographical parameters, to enhance engine efficiency and reduce CO2 emissions [18]. Dornof et al [19] examined the influence of European C-segment passenger car models on the comparison of CO2 emissions under controlled laboratory conditions versus real-world road conditions.…”