Dr Shengan Wang

Intelligent multiphase flow sensing and big data analysis  

Multiphase flow exists widely in biological, chemical and industrial processes. Representative examples include oil/gas/water flow in oil and gas industry, micro-fluidic systems in biomedical research, gas/solid flows in chemical processes and gas/liquid flows in carbon-capture systems. Accurate monitoring and measuring these flows is of paramount significance to not only fundamental research of flow dynamics but also engineering applications, due to the fact that the solution to this problem is essential for relevant industries to reduce cost and emission, improve efficiency and optimise management. This project aims to develop an intelligent multiphase flow-sensing platform for real-time and quantitative monitoring of multiphase flow.   

The project, which began in 2020 and runs until 2023, contains three stages:(1) Multiphase flow data generation and collection stage; (2) Data-driven modelling stage;(3) Intelligent multiphase flow metering platform assessment stage. 

The research is now in the second stage. In this stage, data-driven model will be investigated to solve the image reconstruction problem and improve measurement accuracy of key flow parameters. In addition, transfer learning will be studied to improve the generalisation ability of the data-driven models. 

The objective of this project is to approach the multiphase flow measurement challenge in a radically innovative way by combining multi-modal sensors and data-driven algorithms. We are focusing on developing a low cost, accurate multiphase flow metering platform, which will have great potential to be adopted on a wide scale by energy industries, e.g. oil & gas industries and chemical industries. 

The objective links directly to the strategic planning of digital transformation of the energy industry in the UK. As an emerging area of research inspired by data-driven innovation, the project involves developing and integrating multi-physics flow sensing modalities, and exploiting the information-redundancy and data patterns associated with each data stream and as a whole. By making use of data science, relations between raw sensor signals and the key parameters of multiphase flows will be established, and other useful information (e.g. process fault diagnosis and prognosis) will be distilled from sensors’ outputs.  

This TRAIN@Ed project has received funding from the DDI programme, the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 801215. 

Contact email.

Shengan Wang is a is a TRAIN@ED Fellow
Shengan Wang is a is a TRAIN@ED Fellow

Our Women in Data campaign

Image of Natalie Duffield

Natalie Duffield

CEO of InTechnology Smart Cities Ltd

Photo of Hoppers Society Members

University of Edinburgh Hoppers Society

Image of Samantha Rhynas

Samantha Rhynas

Head of Data at Effini & Girl Geek Scotland Leadership Team & PyData Edinburgh Organiser