Yazar "Goel, Uday" seçeneğine göre listele

Listeleniyor 1 - 1 / 1
  • Küçük Resim
    Öğe
    Comparative analysis of regression models to predict the performance of the dual fuel engine operating on diesel and hydrogen gas
    (Elsevier ltd, 2025) S, Priya; Feenita, C.; Goel, Uday; T, Manoranjitham; Duraisamy, Boopathi; Subramanian, Balaji; Ganeshan, Kavitha; Bai, Femilda Josephin Joseph Shobana; Albeshr, Mohammed F.; Pugazhendhi, Arivalagan; Varuvel, Edwin Geo
    Internal combustion engines (ICEs) have long been essential in both the transportation and industrial sectors, providing primary power for vehicles, ships, and machines globally. Optimising the efficiency of ICEs is vital for decreasing their environmental impart, as increased fuel efficiency and lower emissions play a significant role in mitigating the effects of climate change as well as improving air quality. This study employed 15 regression algorithms and machine learning approaches to analyse and anticipate the performance parameters of ICEs that run on hydrogen-diesel in dual fuel mode. The input parameters include engine torque, speed, hydrogen flow rate, brake power and diesel energy share to hydrogen supply and the output parameters are brake specific fuel consumption, brake thermal efficiency, volumetric efficiency and actual air intake. The model's performance is evaluated using five different performance metrics. Among the studied algorithms, the RANSAC Regressor demonstrated exceptional predictive capability, reaching an R-squared value of 0.999, a mean squared error (MSE) of 0.0064, a root mean square error (RMSE) of 0.08, and a mean absolute error (MAE) of 0.057. These outcomes show the algorithm's accuracy and precision in capturing the complicated data of engine system. The equivalency ratio, volumetric efficiency, brake thermal efficiency, brake specific fuel consumption, and actual air intake are among the critical performance outputs that are optimised by utilizing key input parameters like engine load, rotational speed, hydrogen flow rate, brake power, and the diesel fuel energy share. This study highlights the significant potential of machine learning in optimising ICE performance, offering a reliable alternative to traditional experimental analysis by reducing both risk and economic costs. The research findings also support the paradigm shift towards intelligent and sustainable energy systems by compellingly advocating for the inclusion of data-driven methodologies in contemporary engine design and operational methods