ADVERTISEMENT

Artificial-Intelligence-Driven Timelines Help Optimize Well Life Cycle

Artificial intelligence (AI) and machine-learning algorithms can enable energy companies to digitally reconstruct well histories using both public and company-specific historical well data. This paper discusses how oil and gas companies are using a new generation of AI-driven applications powered by computational-knowledge graphs and AI algorithms to create a digital knowledge layer for oil and gas wells that provides a timeline of significant well events such as drilling problems, blowout preventer tests, bottomhole-pressure (BHP) measurements, and well interventions. The authors explain how they train the application’s machine-learning algorithms to read hundreds of thousands of historical reports to harvest knowledge about the well and store the extracted knowledge in a digital knowledge layer.

Introduction

Even small improvements in upstream operations efficiency can result in dramatic savings. One way to improve efficiency is through better and faster decision-making, enabled by tools that provide seamless access to both the current state and the full history of wells. Wells’ productive lives can span decades. Their data are scattered across dozens of databases and millions of documents and operational comments. Immeasurable knowledge also lives only in the heads of thousands of experts, many of whom may have retired or will retire soon. It has been estimated that the amount of data oil companies handle doubles every 12–18 months, resulting in an ever-growing data-volume and knowledge problem.

Integrating all relevant information for a well is a lengthy and complex process because of both technical and organizational challenges. Well history is maintained across multiple teams and is encoded in a wide range of documents, drilling comments, and complex semi­structured data sources such as drilling reporting systems and well databases. The longevity of many wells means that technologies used to collect this data have changed over the years, leaving decades of data trapped in silos created by legacy technologies. Wells acquired from partnerships or acquisitions can be even more difficult to integrate because of differing standards and conventions for writing, storing, and naming information.

This article, written by JPT Technology Editor Judy Feder, contains highlights of paper OTC 29487, “AI-Driven Well Timelines for Well Optimization,” by Jeff Dalgliesh, Allen Jones, and Arulmozhi Palanisamy, Maana, et al., prepared for the 2019 Offshore Technology Conference, Houston, 6–9 May. The paper has not been peer reviewed. Copyright 2019 Offshore Technology Conference. Reproduced by permission.
...
This article is reserved for SPE members and JPT subscribers.
If you would like to continue reading,
please Sign In, JOIN SPE or Subscribe to JPT

Artificial-Intelligence-Driven Timelines Help Optimize Well Life Cycle

01 February 2020

Volume: 72 | Issue: 2

No editorial available

ADVERTISEMENT


STAY CONNECTED

Don't miss out on the latest technology delivered to your email weekly.  Sign up for the JPT newsletter.  If you are not logged in, you will receive a confirmation email that you will need to click on to confirm you want to receive the newsletter.

 

ADVERTISEMENT

ADVERTISEMENT

ADVERTISEMENT

ADVERTISEMENT