@ARTICLE{Sakar_Sayantan_Comprehensive_2022,
 author={Sakar, Sayantan and Datta, Deepshikha and Chowdhury, Somnath and Das, Bimal},
 volume={vol. 43},
 number={No 2 (The International Chemical Engineering Conference 2021 (ICHEEC): 100 Glorious Years of Chemical Engineering and Technology, held from September 16–19, 2021 at Dr B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab, India. Guest editor: Dr Raj Kumar Arya, Dr Anurag Kumar Tiwari)},
 journal={Chemical and Process Engineering},
 pages={119-135},
 howpublished={online},
 year={2022},
 publisher={Polish Academy of Sciences Committee of Chemical and Process Engineering},
 abstract={Waste lubricating oil (WLO) is the most significant liquid hazardouswaste, and indiscriminate disposal of waste lubricating oil creates a high risk to the environment and ecology. Present investigation emphasizes the re-refining of used automobile engine oil using the extraction-flocculation approach to reduce environmental hazards and convert the waste to energy. The extraction-flocculation process was modeled and optimized using response surface methodology (RSM), artificial neural network (ANN), and genetic algorithm (GA). The present study assessed parametric effects of refining time, refining temperature, solvent to waste oil ratio, and flocculant dosage. Experimental findings showed that the percentage of yield of recovered oil is to the tune of 86.13%. With the Central Composite Design approach, the maximum percentage of extracted oil is 85.95%, evaluated with 80 minutes of refining time, 50.17 °C refining temperature, 7:1 solvent to waste oil ratio and flocculant dosage of 3 g/kg of solvent and 86.71% with 79.97 minutes refining time, 55.53 °C refining temperature, 4.89:1 g/g solvent to waste oil ratio, 2.99 g/kg of flocculant concentration with Artificial Neural Network. A comparison shows that the ANN gives better results than the CCD approach. Physico-chemical properties of the recovered lube oil are comparable with the properties of fresh lubricating oil.},
 type={Article},
 title={Comprehensive analysis of reclamation of spent lubricating oil using green solvent: RSM and ANN approach},
 URL={http://ochroma.man.poznan.pl/Content/124692/PDF/art03_int.pdf},
 doi={10.24425/cpe.2022.140815},
 keywords={modelling, optimization, extraction-flocculation, artificial neural network, genetic algorithm},
}