Data Analytics on the Phase Behavior of Oil/Water/Surfactant Systems

POSTER

Abstract

According to BP Statistical Review of World Energy in 2018, the total oil production in US in 2017 is about 13 million barrels per day (MBPD), which is even greater than that of Saudi Arabia (less than 12 MBPD). Thanks to the booming shale oil production, United States have become the world’s top oil exporter. In fact, two third of conventional crude oil in US Field is remained unproduced due to the physics of fluid flow. The techniques of chemical enhanced oil recovery could overcome the physical force holding hydrocarbons, and turn these accumulations into oil reserve. To enhance the oil recovery in the reservoir, many efforts have been made to apply surfactants into the injected water. For the oil/water/surfactant system, the goal is to form the phase ‘microemulsion’ to achieve the lowest interfacial tension. Therefore, it is critically important to achieve a great mixing phase behavior for the oil/water/surfactant system. In collaboration with the Pioneer Oil Company, our current effort is to better optimize the selection of surfactants, and the constituents of the surfactant blend, which turns to be a high dimensional problem. In addition to the conventional analysis, we employ the machine learning techniques to solve the system as a multinomial classification problem.

Presenters

  • Shiyan Wang

    Purdue University

Authors

  • Shiyan Wang

    Purdue University

  • Nathan Schultheiss

    Purdue University

  • Sangtae Kim

    Purdue University