Evaluation of the engine performance and exhaust emissions of biodiesel-bioethanol-diesel blends using kernel-based extreme learning machine. (15th September 2018)

• Record Type: Journal Article
• Authors: Silitonga, A.S.; Masjuki, H.H.; Ong, Hwai Chyuan; Sebayang, A.H.; Dharma, S.; Kusumo, F.; Siswantoro, J.; Milano, Jassinnee; Daud, Khairil; Mahlia, T.M.I.; Chen, Wei-Hsin; Sugiyanto, Bambang
• Is Part Of: Energy. Volume 159(2018)
• Page Start: 1075
• Page End: 1087
• Publication Date: 2018-09-15
• Subjects: Biodiesel-bioethanol-diesel blend -- Property -- Engine performance -- Exhaust emission -- Kernel-based extreme learning machine; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2018.06.202
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: It is known that biodiesel and bioethanol are viable alternative fuels to replace diesel for compression ignition engines. In this study, an experimental investigation is carried out to evaluate the performance and exhaust emissions of a single cylinder diesel engine fuelled with biodiesel-bioethanol-diesel blends. The engine performance parameters evaluated are the brake specific fuel consumption and brake thermal efficiency whereas the exhaust emission parameters evaluated are carbon monoxide, nitrogen oxide, and smoke opacity. Kernel-based extreme learning machine is used to predict the engine performance and exhaust emission parameters of the fuel blends at full throttle conditions. Based on the experimental results, the brake specific fuel consumption is lower while the brake thermal efficiency is higher for the biodiesel-bioethanol-diesel blends. The carbon monoxide emissions and smoke opacity are also lower for these fuel blends. The mean absolute percentage error of the brake specific fuel consumption, brake thermal efficiency, carbon monoxide, nitrogen oxide, and smoke opacity is 1.363, 1.482, 4.597, 2.224, and 2.090%, respectively. Thus, it can be concluded that K-ELM is a reliable method to estimate the engine performance and exhaust emission parameters of a single cylinder compression ignition engine fuelled with biodiesel-bioethanol-diesel blends to reduce fuel consumption and exhaust emissions. Highlights: Biodiesel-bioethanol-diesel blends can be used in CI engines without modifications. K-ELM modelling facilitates in minimizing fuel consumption and exhaust emissions. The K-ELM model inputs are the volume ratio of the fuel blends and engine speed. BSFC and CO are the significant engine performance and exhaust emission parameters. The MAPE values are within a range of 1.363–2.090%.