An Expert System Based on Soft Computing Techniques for Monitoring Multiphase Flows

The knowledge and the forecast of the parameters which rule the downflow models in oil extraction and transport are today of paramount importance. In particular the extracted oil is mixed with water and gas in rates which differ not only from different wells, but also on the same well during its life. The main problems involved with the measurement of the flow rates are : well exhaustion, critical flow pattern prevision and pipeline leak detection. Today the production of several wells is carried, with short pipelines, to a manifold from which, with a single long pipeline, the total production is carried to the oil centre. In this situation the information concerning the single well is lost so that the main oil industries require monitoring systems which can indicate the individual well flow rates. So far general measurement systems don’t exist and one of the main goals is the development of an instrumentation tool for the mass flow rate measurement of three phase flows (oil-gas-water). Building a single model for the whole range is very difficult because of the high non-linearity effects due to the variation of flow patterns, liquid viscosity and density and therefore different models for the data analysis, based on different approaches corresponding to different fluidynamic hypothesis, have been developed. In this context building up an effective expert system for monitoring oil fields is a very hard challenge for the main oil companies and research institutes.