Mathematical Models for Predicting the Biodiesel Properties
Constant Bande Bakande1, Youssef Kassem2, Hüseyin Çamur3
1Constant Bande Bakande*, Department of Mechanical Engineering, Faculty of Engineering, Near East University, via Mersin, Turkey, Nicosia, Cyprus.
2Youssef Kassem, Department of Mechanical Engineering, Faculty of Engineering, Near East University, via Mersin, Turkey, Nicosia, Cyprus.
3Hüseyin Çamur, Department of Mechanical Engineering, Faculty of Engineering, Near East University, via Mersin, Turkey, Nicosia, Cyprus.
Manuscript received on February 10, 2020. | Revised Manuscript received on February 27, 2020. | Manuscript published on March 10, 2020. | PP: 2362-2376 | Volume-9 Issue-5, March 2020. | Retrieval Number: E2266039520/2020©BEIESP | DOI: 10.35940/ijitee.E2266.039520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Density, viscosity and cetane number are important physical properties of biodiesel as they participate in one way or another in the fuel metering, calibration and nozzle process during combustion. High and good accuracy of the physical properties of biodiesel will therefore lead to improved combustion and therefore better efficiency. The aim of this study is therefore to seek good and high precision by combining properties and comparing the analysis between ANN and RSM. Studies have been made by researchers to collect data. In this study the combination of properties is exploited. A total of 1360 data from the various studies has been collected and exploited. From this data after elimination and treatment 39 possible combinations were analyzed and compared by ANN and RSM. The result of simulation is: The best combinations: 𝝆 = 𝒇(𝑭𝒂) , 𝝂 = 𝒇(𝑭𝒂) , 𝒄𝒏 = 𝒇(𝑭𝒂) with 𝑹𝟐 respectively equal to (0.9998, 0.9998 , 0.9987) and R equal to ( 0.9997,0.99971,0.9984) obtained with ANN simulation provide more accuracy than 𝑹𝟐 ( 0.912 , 0.799 , 0.766 ) and R ( 0.837, 0.739 , 0.920) obtained with RSM simulation in general 𝑹𝟐 obtained with ANN (0.9998, 0.9998 , 0.9987) provide good accuracy than 𝑹𝟐 (0.9112,0.799,0.766) obtained with RSM . Also there is a good relationship between fatty acid and others properties since they provide good result. In general the overall regression coefficient R and the correlation coefficient 𝑹𝟐 values of the combinations obtained in the simulation with the ANN provide better and good accuracy since their values are close to each other and all close to 1, and their mse tend towards 0. While the one obtained with RSM are distant from each other and distant of 0 so they provide an acceptable accuracy.it is also important to note that high accuracy of properties using RSM must have at least combination of three parameters. Also after every combination, the conclusion says there is a good relationship between fatty acid and other properties. Then for the future work, it will be benefit to combine fatty acid with others properties and evaluate result, also use another network to simulate.
Keywords: Artificial Neural Network, Cetane Number Density, Fatty Acid, Regression Coefficient, Response Surface Methodology, Overall Coefficient, Viscosity.
Scope of the Article: Artificial life and Societies