Prediction of rock strength parameters for an Iranian oil field using neuro-fuzzy method

Uniaxial compressive strength (UCS) and internal friction coefficient (µ) are the most important strength parameters of rock. They could be determined either by laboratory tests or from empirical correlations. The laboratory analysis sometimes is not possible for many reasons. On the other hand, Due to changes in rock compositions and properties, none of the correlations could be applied as an exact universal correlation. In such conditions, the artificial intelligence could be an appropriate candidate method for estimation of the strength parameters. In this study, the Adaptive Neuro-Fuzzy Inference System (ANFIS) which is one of the artificial intelligence techniques was used as dominant tool to predict the strength parameters in one of the Iranian southwest oil fields. A total of 655 data sets (including depth, compressional wave velocity and density data) were used. 436 and 219 data sets were randomly selected among the data for constructing and verification of the intelligent model, respectively. To evaluate the performance of the model, root mean square error (RMSE) and correlation coefficient (R2) between the reported values from the drilling site and estimated values was computed. A comparison between the RMSE of the proposed model and recently intelligent models shows that the proposed model is more accurate than others. Acceptable accuracy and using conventional well logging data are the highlight advantages of the proposed intelligent model.