چکیده مقاله
The Research Octane Number RON is a key indicator of gasoline's anti knock quality and a crucial determinant of engine performance This study aims to establish a fast, accurate, and cost effective method for RON prediction by systematically evaluating a diverse set of machine learning ML algorithms based on molecular descriptors A publicly available Kaggle dataset containing molecular descriptors as input features and RON as the target variable was employed After data preprocessing including removal of irrelevant attributes, a train test split, and feature scaling via StandardScaler, twenty regression models were trained and evaluated Model performance was benchmarked using the coefficient of determination R2 , Mean Absolute Error MAE , and Root Mean Squared Error RMSE Among all models, the Gaussian Process Regressor GPR achieved the highest predictive accuracy with an R2 of 0 94 and the lowest error metrics Ensemble techniques, including XGBoost R2 = 0 90 , CatBoost R2=0 91 , and GradientBoosting R2=0 89 , also exhibited strong and reliable performance Overall, the results demonstrate that advanced non linear regression models are indispensable for precise RON prediction GPR emerged as the most accurate approach, while ensemble models such as XGBoost offered an excellent compromise between accuracy and computational efficiency, making them promising candidates for industrial scale deployment
کلیدواژهها
نویسندگان
Salar Hadadian Dehkordi
M Sc Student in Reservoir Engineering, Ahvaz Faculty of Petroleum, Petroleum University of Technology, Ahvaz, Iran
شیوه ارجاع
Hadadian Dehkordi, Salar,1404,A Comprehensive Comparative Analysis of Machine Learning Models for Accurate Prediction of Research Octane Number (RON),The 8th international conference on artificial intelligence and its future prospects in electrical, computer, mechanical and telecommunication engineering sciences,Mashhad
ارائهشده در
مجموعه مقالات هشتمین کنفرانس بین المللی هوش مصنوعی و چشم انداز آینده آن در علوم مهندسی برق ، کامپیوتر ، مکانیک و مخابرات5 آذر 1404 · مشهد