Spe-192002-ms case Study Applied Machine Learning to Optimise pcp completion Design in a cbm field

Document Outline

• Case Study Applied Machine Learning to Optimise PCP Completion Design in a CBM Field
  • Introduction
    • PCP Pump Failures
    • Data Requirements / SCADA / Completion Data
  • Stationary representations of a CBM Well
    • Material Balance Modeling
    • Stationary Representation
  • GPR for PCP Runlife
    • Covariance and Hyper-parameters
    • Likelihood and Bayesian Inference
  • Discussion
    • Censored data and multiple failure modes
    • Data Exploration and Feature Importance
    • Grid Search Optimisation
  • Conclusions
• References