Developing a Hybrid Data-Driven, Mechanistic Virtual Flow Meter - a Case Study

  title={Developing a Hybrid Data-Driven, Mechanistic Virtual Flow Meter - a Case Study},
  author={Mathilde Hotvedt and Bjarne Grimstad and Lars Struen Imsland},

Figures and Tables from this paper

Passive learning to address nonstationarity in virtual flow metering applications

When is gray-box modeling advantageous for virtual flow metering?

On gray-box modeling for virtual flow metering

Development of a Virtual Flowmeter as an Enhanced Alternative for Field Production Monitoring

The VFM approach developed in this work combines black-box simulations with mixed-integer linear programming (MILP) problem to obtain the flowrates dismissing the tuning process and believes that the tuning-free method can contribute to the future of VFM technologies.

Identifiability and interpretability of hybrid, gray-box models

This work illustrates by means of an industrial case study, modeling of a production choke valve in a petroleum well, how physical interpretation of the physical model parameters may be preserved for non-identifiable models by utilizing parameter regularization in the estimation problem.



A Hybrid Ensemble-Based Approach for Process Parameter Estimation and Degradation Assessment in Offshore Oil Platforms

This paper resorts to hybrid modelling which integrates the physics-based model into an ensemble of data-driven models built using Kernel Regression methods, and the proposed hybrid ensemble-based approach is verified on real measurements performed on offshore choke valves located topside at different wells.

Hybrid semi-parametric modeling in process systems engineering: Past, present and future

A hybrid neural network‐first principles approach to process modeling

A hybrid neural network-first principles modeling scheme is developed and used to model a fedbatch bioreactor. The hybrid model combines a partial first principles model, which incorporates the

A Systematic Grey-Box Modeling Methodology via Data Reconciliation and SOS Constrained Regression

A nonlinear optimization of limited complexity is to be solved in the DR stage and the proposed constrained regression is based in sum-of-squares (SOS) convex programming and several desirable features on the polynomial regressors can be naturally enforced in this optimization framework.

Multiphase Flow Metering: Current Trends and Future Developments

Over the last decade, the development, evaluation, and use of multiphase-flow-metering (MFM) systems have been a major focus for the oil and gas industry worldwide. Many alternative metering systems

Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation

The best method for process control is the use of model-based solutions, based on process analytical technology for online monitoring of critical process variables, product quality attributes, or a

Wet Gas Metering Using a Revised Venturi Meter and Soft-Computing Approximation Techniques

Results obtained by using an industrial-scale test rig suggest that the flow rate of wet gas flowing in the TEVM is related not only to the static features but also to the dynamic features of the differential pressures across the converging and the extended throat sections of the Venturi meter.

High-Throughput Microfiltration Membranes with Natural Biofouling Reducer Agent for Food Processing

The effect of natural antibiotics Moringa oleifera seeds powder in cellulose acetate membranes as biofouling reducer agent was investigated. Mixed matrix membranes (MMM) were synthesized by adding