Improving Multiphase Flow Metering performance using Artificial Intelligence algorithms

In the petroleum industry the real-time monitoring of producing wells is recognised as the best way of optimising field performance. Monitoring a producing well implies the ability to track, in real-time, any changes in fluid composition, flow rates, or pressure and temperature profiles. Multiphase Flow Metering (MFM) plays a key role in this scenario. The most discussed aspect in MFM concerns flow modelling. Different approaches have been followed highlighting the non uniqueness of solutions. Therefore, it seems that an integrated approach between mechanical models and artificial intelligence model could be a better solution in metering. Moreover, such information, combined with the critical analysis of historical data from the well itself or from analogue wells, allows diagnosis of the system and prediction of future trends. This paper suggests how MFM, Artificial Neural Networks (ANN) and Fuzzy Logic (FL) can offer an integrated solution to MFM in field. During a field test 10 month long data have been gathered and processed to have a flow rate monitoring. From results, it appears that ANNs and FL can be combined with Fluid dynamic Models to provide not only a real-time monitoring of produced flow rates and stream composition, but also a valid quality check of information. Field data and predicted data can be checked against each other, so that it becomes possible, via application of AI techniques, to distinguish between changes in the actual flow conditions of the production system and re-calibration issues related to the metering devices.