|
|
|
|
LEADER |
03161nam a2200469Ia 4500 |
001 |
10.1016-j.egyr.2022.06.052 |
008 |
220718s2022 CNT 000 0 und d |
020 |
|
|
|a 23524847 (ISSN)
|
245 |
1 |
0 |
|a Modelling and prediction approach for engine performance and exhaust emission based on artificial intelligence of sterculia foetida biodiesel
|
260 |
|
0 |
|b Elsevier Ltd
|c 2022
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1016/j.egyr.2022.06.052
|
520 |
3 |
|
|a 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)
|
650 |
0 |
4 |
|a Acid pretreatment
|
650 |
0 |
4 |
|a Biodiesel
|
650 |
0 |
4 |
|a Blended fuels
|
650 |
0 |
4 |
|a Diesel engine
|
650 |
0 |
4 |
|a Diesel engines
|
650 |
0 |
4 |
|a Diesel fuels
|
650 |
0 |
4 |
|a Emission characteristic
|
650 |
0 |
4 |
|a Emission characteristics
|
650 |
0 |
4 |
|a Engine performance
|
650 |
0 |
4 |
|a Exhausts emissions
|
650 |
0 |
4 |
|a Forecasting
|
650 |
0 |
4 |
|a Knowledge acquisition
|
650 |
0 |
4 |
|a Learning machines
|
650 |
0 |
4 |
|a Machine learning
|
650 |
0 |
4 |
|a Modelling and predictions
|
650 |
0 |
4 |
|a Neural networks
|
650 |
0 |
4 |
|a Pretreatment process
|
650 |
0 |
4 |
|a Refining process
|
650 |
0 |
4 |
|a Smoke
|
650 |
0 |
4 |
|a Sterculia foetida
|
700 |
1 |
|
|a Alfansuri, M.
|e author
|
700 |
1 |
|
|a Fayaz, H.
|e author
|
700 |
1 |
|
|a Kusumo, F.
|e author
|
700 |
1 |
|
|a Milano, J.
|e author
|
700 |
1 |
|
|a Prahmana, R.A.
|e author
|
700 |
1 |
|
|a Sebayang, A.H.
|e author
|
700 |
1 |
|
|a Shamsuddin, A.H.
|e author
|
700 |
1 |
|
|a Silitonga, A.S.
|e author
|
700 |
1 |
|
|a Zamri, M.F.M.A.
|e author
|
773 |
|
|
|t Energy Reports
|