Appraising machine learning algorithms in predicting noise level and emissions from gasoline-powered household backup generators

Abstract

Machine learning is presently receiving great attention. However, machine learning applications to gasoline engine research are limited. This paper investigated the implementation of various machine learning models in predicting the emissions (CO₂, CO, and PM_2.5) and noise levels of gasoline-powered household generators for the first time. Data of operating and installed capacity, efficiency (input) and emissions, and noise level (output) obtained from 166 generators were used in extreme gradient boosting, artificial neural network (ANN), decision tree (DT), random forest (RF), and polynomial regression (PNR) algorithms to develop predictive models. Results revealed high prediction performance (R² = 0.9377–1.0000) of these algorithms marked with very low errors. The implementation of PNR followed by the RF exhibited the best models for predicting CO₂, CO, PM_2.5, and the noise level of generators. R² of 1.000 and 0.9979–0.9994, mean squared error of < 10⁻⁶ and 2 × 10⁻⁵–8.6 × 10⁻⁵, mean absolute percentage error of 9.15 × 10⁻¹⁶–1.3 × 10⁻¹⁵ and 7.1 × 10⁻³–8.1 × 10⁻², and root mean squared error of 3.3 × 10⁻¹⁶–5.4 × 10⁻¹⁶ and 4.4 × 10⁻³–9.3 × 10⁻² were recorded for all the output parameters using PNR and RF respectively. DT models had the least prediction capacity for CO, CO₂, and noise levels (R² = 0.9493–0.9592) while ANN produced the least performance for PM_2.5 (R² = 0.9377). This study further strengthens machine learning applications in engine research for the prediction of various output parameters.