Machine-Learning Model Improves Gas Lift Performance and Well Integrity

The main objective of this work is to use machine-learning (ML) algorithms to develop a powerful model to predict well-integrity (WI) risk categories of gas-lifted wells. The model described in the complete paper can predict well-risk level and provide a unique method to convert associated failure risk of each element in the well envelope into tangible values.

ML Model

The model can be subdivided into four submodels as follows:

• The predictive model, which predicts the risk status of wells and classifies their integrity level into five categories rather than three broad-range categories, as in qualitative risk classification. The five categories are
  
  • Category 1, which is too risky
  • Category 2, which is still too risky but less so than Category 1
  • Category 3, which is medium risk but can be elevated if additional barrier failures occur
  • Category 4, which is low risk but features some impaired barriers
  • Category 5, which is the lowest in risk
• The failure model, which identifies whether the well is considered to be in failure mode. In addition, the model can identify wells that require prompt mitigation.
• The suboptimal model, which identifies wells operating out of the integrity envelope.
• The diagnosis model, which locates the root of cause of WI impairment and introduces an action plan.

This classification was performed using ML algorithms such as logistic regression, decision trees, random forest, Gaussian, K-nearest neighbor, and support-vector machine classifiers.

Steps of Building the Model.