Digital twins for multiphase flow systems

Integrating data, physics and machine learning to develop rapid predictive models for engineered multiphase flow systems

Project status



Data-informed 'digital twins' of complex systems are seeing adoption in design, manufacturing and distribution. In the energy and manufacturing sectors, digital twins are living models that drive operational efficiency and process safety outcomes. This project works across the key enablers of digital twin technology; cloud computation, internet-of-things (IoT) sensor networks, advances in machine learning and interactive data visualisation; in order to develop rapid predictive models for engineered multiphase flow systems.

Explaining the science

Process engineering within the energy and manufacturing sectors relies on a thorough understanding of multiphase flow systems. Systems comprising liquids, gases and solid particles are complex to control and feature poorly understood dynamics regarding phase formation and transitions. Digital twin technologies will unlock barriers to operational efficiency and industrial process safety through a fusion of simulation and experimentally derived data streams.

A key metric of digital twin performance is the underlying simulation fidelity. In many engineering cases, physics based models outperform purely statistical models; as limited data are typically available for inference, or data may not exist due to the intrusiveness of measurement techniques. Simulation fidelity, however, comes at a cost: slow computation times limit iteration and parameter-exploration opportunities, while high-resource demands restrict computations to energy-intensive high-performance clusters. New hybrid physics/machine learning models will hence unlock real-time digital twin coupling, and allow for computation on low-intensity cloud resources. A tradeoff between simulation realism and relevancy must be navigated in order to deliver solutions: rapid, low-fidelity solutions can be of high decision-making utility, provided that uncertainty is explicitly quantified.

Advances in machine learning can be exploited to calibrate underlying simulations with physical data streams, leading to rapid prediction tools for complex multiphysics scenarios. This project's focus areas include reduced-order modelling, surrogate modelling and active learning strategies, in addition to numerical solvers for continuum mechanics partial differential equation systems. Incorporating physics based constraints and insights, such as energy/mass conservation and empirical closures, into machine learnt models is a priority.

Project aims

The project will demonstrate value creation and impact within the energy and manufacturing sectors by deploying cloud-native digital twin applications. The project roadmap includes:

  • Performance benchmarking of surrogate modelling and active learning strategies in multiphase flow settings
  • Development of rapid alternatives to existing fluid dynamic solutions by exploiting advances in statistics and machine learning
  • Development of novel predictive models incorporating both physics and data with explicit quantification of uncertainty


Within the energy and manufacturing sectors, digital twin technology will see application in varied multiphase control settings:

  • Safety-critical prediction of reactor entrainment and emergency cooling performance
  • Decontamination modelling for process-equipment product changeover
  • Monitoring and predictive maintenance for flow-induced erosion
  • Materials sensing for environmental flow contamination in porous media
  • Additive manufacture and optimisation of novel reactors for process intensification
  • Design and manufacture of polymer membrane materials


Professor Omar Matar

Data-Centric Engineering Strategic Leader, The Alan Turing Institute & Vice-Dean (Education), Faculty of Engineering, Imperial College London

Researchers and collaborators

Contact info

[email protected]