Neural Network Knowledge-Based Modeling of Rock Properties Based on Well Log Databases

摘要

Analyzing data from well logs is often a complex and laborious process because a physical relationship cannot be established tornshow how the data are correlated. In this paper, we will develop the next generation of "intelligent" software that will extract rockrnproperties and relevant reservoir information from well log databases. Our objective is to develop the next generation ofrn"intelligent" software tools that will extract information from well log databases. The software will use fuzzy logic techniquesrnbecause the data and our requirements are imperfect. In addition, it will use neural network techniques, since the functionalrnstructure of the data is unknown. In particular, the software will be used to group data into important data sets; extract and classifyrndominant and interesting patterns that exist between these data sets; discover secondary, tertiary and higher-order data patterns;rnand discover expected and unexpected structural relationships between data sets.