SPIRIT Integrating Knowledge Based Techniques Into Well Test Interpretation

This article describes how spirit a computer program for well test interpretation wti integrates knowledge based techniques for pattern matching and decision modelling Existing conventionalwti computer software assists reservoir engineers by removing some of the more mundane tasks as well as automating some of the manual interpretation techniques However the software generally provides no guidance to the user on the selection of an appropriatewti model which is a crucial stage in wti The goal of the spirit project was to develop a prototype of the next generation of wti software that included a decision support tool for wti model selection Spirit makes use of several di erent types of information for interpreting a well test pressure seismic petrophysical geological and engineering Spirit s knowledge based approach to type curve matching is to generate several di erent feasible interpretations by making assumptions about the possible presence of both wellbore storage and late time boundary e ects Spirit fuses information from the type curve matching and the other data sources using a knowledge based decision model developed in collaboration with a wti expert These knowledge based approaches were integrated with novel smoothing and segmentation algorithms as well as standard wti presentation and analysis methods The resulting prototype system has been judged to be a success by sponsors of the work