When I was a chemical engineering student, my cohort joked about the relative merits of McCabe-Thiele and Ponchon-Savarit (graphical distillation design methods) and which of these they liked better. Perhaps as a petroleum engineering student, you did the same with Horner and Blasingame. While still useful for understanding the basic physics behind design, by the 1990s, actual equipment design and performance assessments already were being performed typically by increasingly sophisticated computer programs. These programs would eventually invert problems such as these, from one in which the performance of a design is demonstrated to one in which an optimization problem is specified and then iterated to find the best design. The movement away from graphical design methods to physics-based modeling was an inflection point with profound effects—for example, pilot plants mostly disappeared while confidence in engineering outcomes dramatically improved.
We are approaching a similarly profound inflection point. Many of the advances that will drive this transition have already happened, such as bandwidth and computing costs dropping to almost nothing with access becoming nearly universal, sensors becoming plentiful and the information they provide increasingly rich, and business models changing from a buy/own/use approach to an everything-as-a-service model. Business opportunities now no longer wait for needed technology, but they may be limited by the rate at which we adapt our processes and culture.
In recent years, we have seen that the papers highlighted in this section have detailed corporate aspirations, science projects that pointed to the potential of coming technologies, and early proofs of concepts and case studies highlighting learnings. As you read the examples in this section, you will see that a change is already under way in that the methods that are being used are increasingly not oil-and-gas-specific but instead follow patterns that are being used in other industries that are perhaps a bit further into the transformation.
It is my hope that these examples will challenge and inspire. If you are an academic, will your students be ready to practice the transformed work flows that are coming? If you are a provider, are you anticipating how your services will evolve and take advantage of other emerging services? For the operator, are you evolving your capabilities, developing your staff, and working closely with the right partners to position your future success?
This Month's Technical Papers
Analytics Solution Helps Identify Rod-Pump Failure at the Wellhead
Machine Learning Optimizes Duvernay Shale-Well Performance
Augmented Artificial Intelligence Improves Data Analytics in Heavy-Oil Reservoirs
Recommended Additional Reading
SPE 192627 Digitalization of a Giant Field—The Rumaila Story by Yaser Salman, Rumaila Operating Organisation, et al.
SPE 190827 Field-Scale Production Optimization With Intelligent Wells by Osho Ilamah, Nexen, et al.
SPE 189808 Data-Based Smart Model for Real-Time Liquid-Loading Diagnostics in Marcellus Shale Through Machine Learning by Amir Ansari, West Virginia University, et al.
| John Hudson, SPE, has more than 25 years of experience in subsurface software, flow assurance, production-system design, and technology development. He has held technical and managerial positions in Shell at locations in Europe and North America, providing consultancy to a diverse set of assets globally. His activities have included the development of a model-based, cloud-deployed, real-time operational support system for major gas-production systems. He is currently Americas regional support and deployment manager for subsurface and wells software. Hudson holds a PhD degree in chemical engineering from the University of Illinois. He serves on the JPT Editorial Committee and can be reached at www.linkedin.com/in/hudsonjohnd. |
