Cognitive Model to Estimate Static Formation Temperatures in Oil Wells: Inverse Problem

Abstract

A cognitive model was developed to solve an inverse heat transfer problem of estimating static formation temperatures (SFTs) from logged temperatures in oil wells. The cognitive model is based on formulation of a human expert knowledge with uncertainty, which is expressed in terms of fuzzy rules. Thus, mathematically speaking, an inverse heat transfer problem was solved in this way, based on reactive decision model. The performance of the present method of inverse problem is evaluated by means of oil well C-3007 from the maritime zone of the Gulf of Mexico. The results were compared with the Horner method. It was found that the cognitive method is very accurate, as well as efficient, due to the fact that the SFT can be obtained with only temperature log for each depth.

Keywords:

• artificial intelligence
• cognitive models
• inverse problem
• reactive agents
• temperature formation