Developing correlations by extreme learning machine for calculating higher heating values of waste frying oils from their physical properties

• Published in: Neural computing & applications 2017-11, Vol.28 (11), p.3145-3152
• Main Authors: Ertuğrul, Ömer F., Altun, Şehmus
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Artificial neural networks; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Correlation; Data Mining and Knowledge Discovery; Extreme values; Frying; Heating; Image Processing and Computer Vision; Laboratory equipment; Machine learning; Mathematical analysis; Neural networks; Original Article; Physical properties; Probability and Statistics in Computer Science; Training; Vegetable oils; Viscosity
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-016-2233-8

In this study, a novel approach was proposed based on extreme learning machine (ELM) for developing correlations in order to calculate higher heating values (HHVs, kj/kg) of waste frying oils from their physical properties such as density ( ρ , kg/m 3 ) and kinematic viscosity ( v , mm 2 /s) values. These values can easily be determined by using laboratory equipment. For developing the correlations, an experimental dataset from the literature covering 35 samples was collected to be employed in the training and validation steps. The obtained optimum parameters of artificial neural network in the training stage by ELM were employed to develop new correlations. The HHVs calculated by using density-based correlation (HHV = 50823.183 − 12.34095 ρ ) showed the mean absolute and relative errors of 145.8048 kJ/kg and 0.3695 %, respectively. In the case of the viscosity-based correlation (HHV = 40172.85 − 17.93615 v ), they were found as 129.04 kJ/kg and 0.327 %, respectively. Additionally, new correlations were performed better than those available in the literature and those obtained by other machine learning methods; therefore, it is highly suggested that the proposed approach can be used for developing new correlations.