Skip to main content
Loading

Applied Digital Rig Automation

Tuesday, 17 March
Grand Ballroom C
Technical Session
This session will explore the integration of various automated modeling and monitoring solutions centered on improving Rig Efficiency. Presenters will detail how hybrid models, pattern recognition algorithms, deep reinforcement and unsupervised learning have produced gains through consistency and quality in operations.
Session Chairpersons
Adebowale Solarin - Noble Drilling Corporation
Derek Adam - Oxy
  • 1015-1040 230671
    Physics-based And Data-driven Models: Blending The Best Of Two Worlds To Enable Seamless Well Protection
    P. Arevalo, Baker Hughes INTEQ; L. Katzmann, F. Schuberth, J. Macpherson, Baker Hughes; M. Lien, S. Hovda, Equinor ASA
  • 1040-1105 230680
    Large Scale Impacts And Key Insights From Implementing Pattern Recognition Algorithms To Automated Taring Process
    M.E. Kaya, D. Dunbar, A. Groh, Patterson-UTI Drilling Company LLC
  • 1105-1130 230679
    Predictive Generator Management For Drilling Operations: A Deep Reinforcement Learning Framework
    M. Zhang, A. Groh, J. Harrist, M. Snijder Van Wissenker, Patterson-UTI Drilling Company LLC
  • 1130-1155 230672
    Real-time Detection Of Mud Pump Failures Using Unsupervised Learning On High-frequency Rig Data
    B. Reinoso, Nabors Industries
  • Alternate 230681
    An Integrated Data-driven Workflow For Optimizing Drilling Design In Brazilian’S Offshore Wells
    A.A. Ferro, E.A. Bezerra Silva, F.A. Binas Jr, L.P. Gouveia, A.S. Barboza, Federal University of Alagoas; A.F. Riente, Petrobras
  • Alternate 230683
    Safer And More Efficient Managed Pressure Tripping Operations
    S. Callerio, University of Texas At Austin; P. Ashok, E. van Oort, The University of Texas At Austin; M. Kvalo, Stasis Drilling Solutions