Soft computing-based prediction of porosity for a fractured granite basement reservoir | |
| Author | Nakaret Kano |
| Call Number | AIT Thesis no.GE-13-07 |
| Subject(s) | Reservoirs--Vietname--Cuu Long Basin Soft computing |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Geotechnical and Earth Resources EngineeringWith Specialization in Geosystem Exploration and Petroleum Geoengineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. GE-13-07 |
| Abstract | Fractured granite basement reservoirs are of aparticular interest in Vietnam, where more than 80% of total HC production has come from this type of reservoir for the last 25 years. Notably, in the Cuu Long basin of Vietnam most of oil and gas producing fields are from the fractured granite basement. As a particular feature, the secondary (fracture) porosity that was formed during fracturing and weathering of the basement makes formation evaluation more difficult to be donethan for clastic reservoirs. In this research, well log data from two wells were interpreted to find out the fracture porosity of the fractured basements using a conventional method proposed by Elkewidy and Tiab (1998) and five soft computing techniques,including Artificial Neural Network (ANN), Fuzzy Inference System with Mamdani’s Style, Fuzzy Inference System with Sugeno’s style, Fuzzy Subtractive clustering and Adaptive Neuro-Fuzzy Inference System (ANFIS). The conventional technique used in this study,produced good results in estimation of fracture porosity,which was foundbetween 0.01 and 2.23 percent for well BHX-1 and between 0.15 and 6.63 percent for well BHX-2, respectively. The results from the conventional method were used as targets for soft computing techniques.The soft computing techniques were used to predict fracture porosity of formation. Input variables consisted of Gamma ray, Shallow resistivity, Deep resistivity, Bulk density, Neutron porosity, Photo electric factor, Interval transit time, Hole size. ANN and ANFIS provided excellent results of predicted fracture porosity as indicated by high values of correlation coefficient. ANN was found to bethe easiest and fastest algorithm for predicting fracture porosity in this study. |
| Year | 2014 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. GE-13-07 |
| 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 Phienwej;Surachet Pravinvongvuth; |
| Scholarship Donor(s) | Royal Thai Government Fellowship; |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2014 |