Machine Learning Approach for Single Phase and Multiphase Flow Leak Detection and Monitoring in Onshore/Offshore Pipelines and Subsurface Sequestration Sites

The proposed project will conduct several experimental and numerical modelling to take into consideration a wide range of hydrodynamic, geometric and operating conditions in multiphase flow environment with help of digital twin. We will develop a coupled CFD tool using commercial code (ANSYS and OLGA) and a systematic leak detection methodology for the operators using the digital twin so that they can use the developed technology for pipeline leak detection and location identification with varying operating, hydrodynamic and geometric conditions with improved accuracy, reliability, and sensitivity avoiding any false alarm. The development of this technology in a country like Qatar which is predominantly oil and gas driven will present a unique opportunity for increased efficiency in oil and gas transportation, resulting in lower capital and energy overheads, and savings of millions of dollars every month. The intended technology of multiphase flow leak detection in harsh environment will also add to the knowledge pool with a range of applications, bringing foreign investments as well as international recognition to Qatar.

Develop a multiphase flow leak detection model and visualization tool that is ready to be used by the industry integrating the machine learning and digital twin technique. The proposed novel digital twin for leak detection will be used by industry for accurate prediction of the location, size, number and orientation of both small chronic leaks and larger leaks with improved sensitivity, reliability and robustness. The ultimate goal is to take preventive action by artificial intelligence without requiring human interference