Author/Authors :
Fattahi Hadi نويسنده Department of Mining Engineering, Arak University of Technology, Arak , Nazari Hosnie نويسنده Department of mining Engineering - Arak University of Technology, Arak , Molaghab Abdullah نويسنده National Iranian South Oil Company, Ahvaz
Abstract :
Shear wave velocity (Vs) data are key information for petro-physical, geophysical and geomechanical studies. Although compressional wave velocity (Vp) measurements are available in almost every well, shear wave velocity is usually not recorded for most of old wells due to the technological limitations. Furthermore, measurement of shear wave velocity comparatively costly. This study proposes a novel methodology to tackle these problems by taking advantage of Hybrid Adaptive Neuro Fuzzy Inference System (ANFIS) with Ant Colony Optimization algorithm (ACO) based on Fuzzy C–Means Clustering (FCM) and Subtractive Clustering Method (SCM). The ACO is combined with two ANFIS models for determination of the optimal value of its user–defined parameters. The optimization implementation by the ACO significantly improves the generalization ability of the ANFIS models. These models are used in this study to formulate conventional well log data into Vs in a swift, economical, and accurate manner. A total of 3030 data points were used for model construction and 833 data points were employed for assessment of ANFIS models. Finally, a comparison among ANFIS models, and six well–known empirical correlations proved that ANFIS models can outperform the other methods. This strategy was successfully applied in the Marun reservoir, Iran.
