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

The assessment of artificial intelligence (AI) application for prediction of internal combustion engine (ICE) performance and its impact on CO2 emissions is conducted in this paper. Three machine learning techniques (Random Forest, Support Vector Regression, and Semi-supervised Deep Fuzzy C-means) are developed to analyze inputs from an engine simulation software package database. By employing these sophisticated mathematical techniques, we successfully assess the influence of engine power range on CO2 emissions in this paper. Moreover, the framework facilitates segment-based analysis, which enables segment-specific assessment of CO2 emission based on metrics such as average traveled distance and average daily trips in urban and rural settings. The Deep Fuzzy C-means model (DFCM) seems promising to predict engine performance, with high predictive accuracy and a coefficient of determination (R2) approaching unity. The results indicate that integration of inter-class and intra-class distinctions, along with considering the interquartile range of engine power provides invaluable insights for the formulation of strategies aimed at overhauling the passenger vehicle fleet and advancing decarbonization efforts. By implementing the proposed innovative techniques, we aspire to enrich the precision of ICE emission models, leading to more reliable calculations and an enhanced understanding of the environmental implications associated with vehicles.