DSDE: In Practice

As companies begin to embrace the concepts of digitalization and big data, the main challenge remains: How do we make a step change in reducing human error in heavily paper-based operating and maintenance procedures?

Recent advances in data technology and machine learning have disrupted many businesses and processes and can lead to a new paradigm in workplace safety as well. This case study demonstrates the application of data science and predictive analytics to aid the health, safety, and environment function.

A well was drilled into a prospective unconventional mudstone play offshore Norway. Two of five coring runs were successful while the rest yielded little to no core recovery. Subsequent investigation of the core substantiated that the coring issues largely had natural causes.

The traditional subsea tieback model is evolving, supported by advances in flow assurance that allow tiebacks over much longer distances and by the introduction of new technologies that increase overall cost effectiveness.

Often it is too difficult to create the fault conditions necessary for training a predictive maintenance algorithm on the actual machine. A digital twin generates simulated failure data, which can then be used to design a fault-detection algorithm.

An intelligent drilling optimization application performs as an adaptive autodriller. In the Marcellus Shale, ROP improved 61% and 39% and drilling performance, measured as hours on bottom, improved 25%.

A multizone water-injection project has ultimately proved a method of using intelligent completion interval-control valves in place of traditional sand-control completions in soft sand reservoirs.

In the complete paper, the authors revisit fundamental concepts of reservoir simulation in unconventional reservoirs and summarize several examples that form part of an archive of lessons learned.

In the complete paper, a novel hybrid approach is presented in which a physics-based nonlocal modeling framework is coupled with data-driven clustering techniques to provide a fast and accurate multiscale modeling of compartmentalized reservoirs.

In the complete paper, the authors reduce nonuniqueness and ensure physically feasible results in multiwell deconvolution by incorporating constraints and knowledge to methodology already established in the literature.