Open AccessData based sensing of Shale Oil yield in Oil Shale Retorting process
Author(s) -
Hasan Qayyum Chohan,
Iftikhar Ahmad
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/899/1/012009
Subject(s) - oil shale , retort , shell in situ conversion process , shale oil extraction , oil shale gas , shale oil , petroleum engineering , unconventional oil , geology , kerogen , fossil fuel , mining engineering , environmental science , waste management , source rock , engineering , structural basin , paleontology
Oil shale is sedimentary organic rocks that are being converted into useful shale oil and shale gas. North American regions, Canada and China are exploring the oil shale reserves to accommodate the depletion of natural oil and gas resources. Oil shale retorting technology is being utilized to convert the shale rocks into shale oil and shale gas. The major product is oil that is further treated to convert it into gaseous form. In this study, machine learning techniques like ensemble learning (least square boosting and bagging) and artificial neural network (ANN) are employed for data sensing of oil shale retorting process and being compared. Data is generated for ensemble models through MATLAB-Excel-Aspen interfacing. The proposed framework shows that ANN provides higher accuracy as compare to other models for oil shale retorting process for efficient oil recovery.