A.H. Sebayang, Jassinnee Milano, Abd Halim Shamsuddin, Munawar Alfansuri, A.S. Silitonga, Fitranto Kusumo, Rico Aditia Prahmana, H. Fayaz, M.F.M.A. Zamri
Sterculia foetida derived biodiesel is a potential fuel for a diesel engine. The Sterculia foetida biodiesel required a pre-refining process called degumming and an acid pretreatment process before converting them to methyl ester using the transesterification process. This study blended fuel from Sterculia foetida biodiesel and diesel with different volume ratios (5% to 30% of biodiesel blend with 95% to 70% diesel fuel). Sterculia foetida biodiesel and blended fuels met the ASTM D6751 and EN 14214 standards. The blended fuel is examined to obtain its influences on the performance and emission when operating at a diesel engine (1300 rpm to 2400 rpm). From the outcome, the engine performance of the SFB5 blend shows better performance than diesel fuel in terms of BTE (28.84%) and BSFC (5.86%). Artificial neural networks and extreme learning machines were employed to predict engine performance and exhaust emissions. The developed models gave excellent results, where the coefficient of determination is more than 99% and 98% for BSFC and BTE, respectively. When the engine is operated with SFB5, there is a significant reduction in CO, HC, and smoke opacity emissions by 8.26%, 2.08%, and 3.08%, respectively, and at the same time, an increase in CO2 by 3.53% and NOX by 22.39%. The comparison is made with diesel fuel. The extreme learning machine modelling is powerful for predicting engine performance and exhaust emission compared to artificial neural networks in terms of prediction accuracy. Sterculia foetida biodiesel–diesel blends of 5% show its capability to replace diesel fuel by providing engine peak performance than diesel fuel. © 2022 The Author(s)
Department of Mechanical Engineering, Politeknik Negeri Medan, Medan, 20155, Indonesia; Institute of Sustainable Energy, Universiti Tenaga Nasional, Kajang, Selangor, Malaysia; Department of Mechanical Engineering, College of Engineering, Universiti Tenaga Nasional, Kajang, Selangor, Malaysia; Department of Mechanical Engineering, Faculty of Engineering, Universitas Muhammadiyah Sumatera Utara, Medan, 20238, Indonesia; Centre for Technology in Water and Wastewater, School of Civil and Environmental Engineering, Faculty of Engineering and Information Technology, University of Technology Sydney, NSW, 2007, Australia; Program Study of Mechanical Engineering, Department of Production and Industrial Technology, Institut Teknologi Sumatera, Lampung, 3536, Indonesia; Modelling Evolutionary Algorithms Simulation and Artificial Intelligence, Faculty of Electrical and electronics Engineering, Ton Duc Thang Unviversity, Ho Chi Minh City, Viet Nam
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock