Prediction of permeability and water saturation using neuron networks and fuzzy logic for a clastic reservoir in the gulf of Thailand | |
| Author | Trinant Foongthongcharoen |
| Call Number | AIT Thesis no.GE-11-11 |
| Subject(s) | Oil well logging--Thailand, Gulf of Oil reservoir engineering--Thailand, Gulf of |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Geosystem Exploration and Petroleum Geoengineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. GE-11-11 |
| Abstract | The study area is located in the n orth ern of Pattani Basin in the Gulf of Thailand . Although the major wells in the interested area did have logging and coring, not all depth intervals could be cored and not all logging curves were measured. Some logs were even missing. Assessment or prediction of petrophysical parameters such as por osity, permeability, and water saturation in uncored intervals and at other wells locations may have an important role in the reserve estimation. To help solving this issue, Back - propagation A rtificial Neur al Network (ANN) and Fuzzy Logic with early stopping method was employed in this study to help estimate permeability and water saturation from well logging data. Well logging data and core measurement of two wells (wells A and B) were studied. Quicklook a nd full well log interpretation were conducted in order to identify reservoir, estimate clay volume, effective porosity, permeability, and water saturation. According to zoning the reservoir, there were 9 reservoir zones in well A as well as there were 16 reservoir zones in well B. Volume of clay was determine based on gamma ray log. The types of clay distribution used the Thomas - Stieber plot method. Predominant type of clay distribution in most reservoirs of well A and B was dispersed. Effective porosity w as calculated by based on density log corrected for clay. Due to MSE of density log corrected for clay is less than the sonic log and neutron - density log corrected for clay. Permeability was defined by poroperm relationship of core data. In this paper, w at er Saturation was estimated by Archie‟s equation, Indonesia equation , Simandoux, Waxman - Smith‟s equation, and Dual water model. However, Indonesia equation was the best equation to estimate water saturation in this field. The Back - propagation ANN and Fuzzy Logic with early stopping method was studied and applied for permeability and water saturation predi ction by using MATLAB software. These data sets were training, validating, and testing of ANN analysis and training and checking of Fuzzy logic . The output data used for training were from core permeability and water saturation . The ANN and Fuzyy Logic model with least performance error was applied for permeability and water saturation prediction in uncored well and other wells locations. ANN an alysis and Fuzzy logic, which were Fuzzy subtractive clustering and Fuzzy C - mean clustering, used the well logging data as input layer with the standard set consisting of; gamma ray, deep resistivity, medium resistivity , density, and neutron porosity. The target output data were core permeability and water saturation measurements. According to scenario of ANN and Fuzzy logic both two types; Subtractive and C - mean clustering in Appendix F, they were found that Fuzzy subtractive was the optimal model to predi ct permeability and water saturation of well A and B in this field due to the least of MSE with comparison other models. |
| Year | 2012 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. GE-11-11 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Civil and Infrastucture Engineering (DCIE) |
| Academic Program/FoS | Geotechnical Engineering (GE) |
| Chairperson(s) | Pham Huy Giao; |
| Examination Committee(s) | Noppadol Phien-Wej;Christopher Platt; |
| Scholarship Donor(s) | Royal Thai Government Fellowship; |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2011 |