Enabling Real-Time Asset Analytics for a Cloud-Based Fiber-Optic Data Management System

Yang, Lei (Baker Hughes, a GE company) | Bale, Derek S. (Baker Hughes, a GE company) | Yang, Don (Baker Hughes, a GE company) | Raum, Matthew (Baker Hughes, a GE company) | Bello, Oladele (Baker Hughes, a GE company) | Failla, Roberto (Baker Hughes, a GE company) | Lerohl, David (Baker Hughes, a GE company) | Knowles, David (Shell Global Solutions US Inc) | Kwari, Andy (Shell Global Solutions US Inc) | Cannon, Matt (Shell Global Solutions US Inc) | Ye, Shuzhen (Shell Global Solutions US Inc)

OnePetro 

Abstract

The distributed nature of fiber-optic measurements such as distributed temperature sensing (DTS), distributed acoustic sensing (DAS), and distributed strain sensing (DSS) enables nearly continuous monitoring of the downhole environment in both space and time. Though continuous monitoring opens the door to a rich new set of asset management applications, it comes with its own set of challenges in terms of data transmission, management, and security. Recently, cloud-based fiber-optic data management services have been successfully introduced to the oil and gas industry as an effective way to collect, transfer, store and display distributed measurement data from the downhole environment. To maximize the value of such cloud-based data management systems, and further improve the return on investment for asset managers, the large volume of distributed sensing data collected must be converted to value in a simple and easy-to-use form, depending on different applications. Traditionally, interpretation of distributed sensing data is a manual process conducted by engineers in a post-job workflow. This paper presents the successful integration of an analytics library into the cloud-based fiber-optic data management system. This integration enables real-time, and in some cases near real-time, asset decision making. The design of the analytics architecture is open to meet the wide range of application requirements by asset managers. A few application examples of the analytics integration will be presented using real-time data streamed directly from the field.