Integrating Knowledge-Based Techniques Into Well Test Interpretation

Abstract

The goal of the Spirit Project was to develop a prototype of next-generation well-test-interpretation (WTI) software that would include knowledge-based decision support for the WTI model selection task. This paper describes how Spirit makes use of several different types of information (pressure, seismic, petrophysical, geological, and engineering) to support the user in identifying the most appropriate WTI model. Spirit`s knowledge-based approach to type-curve matching is to generate several different feasible interpretations by making assumptions about the possible presence of both wellbore storage and late-time boundary effects. Spirit fuses information from type-curve matching and other data sources by use of a knowledge-based decision model developed in collaboration with a WTI expert. The sponsors of the work have judged the resulting prototype system a success.