Determining petroleum characteristics of rocks

摘要

A method for automatic interpretation of geochemical measurements obtained by pyrolysis of a rock sample to obtain characterization of the organic matter in the sample comprises using rock samples with known petroleum characteristics to train an artificial neural network. The neural network is then used to obtain the parameters for characterizing the organic matter of a rock sample and interpretation of the characterization parameters is refined at the network output by integrating a fuzzy component comprising a parameter "fuzzification" operation.