Publications

A Nuclear Magnetic Resonance (NMR) log provides useful information for petrophysical studies of hydrocarbon bearing intervals. Free fluid porosity (effective porosity), rock permeability and bound fluid volume (BFV) can be obtained by processing and interpreting NMR data. The present study proposes an improved strategy to make a quantitative correlation between the NMR log parameters and well logs by integrating the different intelligent systems using the concept of committee machine. The committee machine with intelligent systems (CMIS) combines the results of Fuzzy Logic (FL), Neuro-Fuzzy (NF), with the Neural Network (NN) algorithms for the overall estimation of the NMR log parameters from well log data. It assigns a weight factor to each of the individual intelligent algorithms, showing its contribution in the overall prediction. The weight factors are derived in two ways: simple averaging and weighted averaging. In the weighted averaging method, a genetic algorithm (GA) is employed to obtain the optimal contribution of each algorithm in the construction of the CMIS. The petrophysical logs from two wells are used for constructing the intelligent models and a third well from the field is used to evaluate the reliability of the developed models. The results indicate that the higher performance of the GA can optimized the model and is better than the individual intelligent systems performing alone.