Gradient Boosting Machine for Performance and Emission Investigation on Diesel Engine Fueled with Pyrolytic-Biodiesel and 2-Ehn Additive

Machine learning is a branch of artificial intelligence. From the beginning of artificial intelligence to the present, the interest in machine learning has gradually increased. Today, it has a wide range of independent uses such as industry, medicine, robotics, security, e-commerce and engineering. Gradient boosting machines (GBM) are one of the powerful machine learning techniques that have shown remarkable success in a wide variety of practical applications. This paper discusses the effect of 2-EHN addition to biodiesel-waste tire pyrolysis oil (WTPO) binary blends on the performance and emissions of CI engine using GBM algorithm. Experimental data obtained from the studies carried out in Yıldız Technical University were used in the training of the model. With the help of RMSE (root-mean-square error), R 2 (R squared error) and MAE (mean absolute error) value, it was ensured that the network successfully predicted fuel consumption and emissions of CO 2 (carbon dioxide), CO (carbon monoxide), NOx (nitrogen oxides), HC (Hydrocarbon). After making sure of the model's success, fuel consumption and emissions were estimated at two specific revs: maximum torque (1500 rpm) and maximum power (2800 rpm). The results obtained were compared with the literature and were found to be in good agreement