Well log data are routinely used for stratigraphic interpretation of the earth's subsurface. This paper investigates using a co-evolutionary fuzzy system to generate a well log interpreter that can automatically process well log data and interpret reservoir permeability. The methodology consists of 3 steps: 1) transform well log data into fuzzy symbols which maintain the character of the original log curves; 2) apply a co-evolutionary fuzzy system to generate a fuzzy rule set that classifies permeability ranges; 3) use the fuzzy rule set to interpret well logs and infer the permeability ranges. We present the developed techniques and test them on well log data collected from oil fields in offshore West Africa. The generated fuzzy rules give sensible interpretation. This result is encouraging in two respects. It indicates that the developed well log transformation method preserves the information required for reservoir properties interpretation. It also suggests that the developed co-evolutionary fuzzy system can be applied to generate well log interpreters for other reservoir properties, such as lithology. © 2008 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Yu, T., & Wilkinson, D. (2008). A co-evolutionary fuzzy system for reservoir well logs interpretation. Studies in Computational Intelligence, 86, 199–218. https://doi.org/10.1007/978-3-540-75771-9_9
Mendeley helps you to discover research relevant for your work.