On gray-box modeling for virtual flow metering

TL;DR

This paper evaluates five gray-box modeling approaches for virtual flow meters in petroleum production, aiming to improve prediction accuracy and scientific consistency using real historical data from multiple wells.

Contribution

It provides a comparative analysis of different gray-box models for VFMs, highlighting their potential and challenges in balancing physics-based and data-driven learning.

Findings

Prediction error ranged from 1.8% to 40.6%.

Gray-box models can outperform purely mechanistic models.

Balancing physics and data remains a complex challenge.

Abstract

A virtual flow meter (VFM) enables continuous prediction of flow rates in petroleum production systems. The predicted flow rates may aid the daily control and optimization of a petroleum asset. Gray-box modeling is an approach that combines mechanistic and data-driven modeling. The objective is to create a computationally feasible VFM for use in real-time applications, with high prediction accuracy and scientifically consistent behavior. This article investigates five different gray-box model types in an industrial case study using real, historical production data from 10 petroleum wells, spanning at most four years of production. The results are diverse with an oil flow rate prediction error in the range of 1.8%-40.6%. Further, the study casts light upon the nontrivial task of balancing learning from both physics and data. Consequently, providing general recommendations towards the suitability of different hybrid models is challenging. Nevertheless, the results are promising and indicate that gray-box VFMs may reduce the prediction error of a mechanistic VFM while remaining scientifically consistent. The findings motivate further experimentation with gray-box VFM models and suggest several future research directions to improve upon the performance and scientific consistency.