Multiphase Flow Systems and Potential of Machine Learning Approaches in Cutting Transport and Liquid Loading Scenarios

• Main Authors: Saad Khan, M., Barooah, A., Lal, B., Azizur Rahman, M.
• Format: Book
• Published: Springer Nature 2023
• Online Access: http://scholars.utp.edu.my/id/eprint/38047/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174767536&doi=10.1007%2f978-3-031-24231-1_3&partnerID=40&md5=d726cf4d8449c9077fbde4c2c017686a

Multiphase flow is a primary concern in flow assurance applications, mainly dealing with cutting transport, hydrate formation, and liquid loading issues. The conventional prediction model includes empirical equations and complex physics-based models; however, they are limited within the experimental ranges. Due to complex physics and the limitations of numerical methods, new techniques of collecting and evaluating multiphase behavior in these pipelines is essential, which is reviewed in this chapter. The review covers the overview of different multiphase systems, followed by cutting transport and existing models for accurate prediction of cutting transport. Also, the available literature on machine learning applications in cutting transport is included in it. Moreover, the chapter also demonstrates a liquid loading issue and their available prediction methods. The available literature on machine learning in liquid loading applications is also part of this chapter. The final part of the chapter includes the case studies of machine learning in multiphase flow systems to provide the field applicability of this modern prediction technique which can provide an avenue for future applications. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.