Loading...

Cement Quality Investigation and Determination Using Automatic Interpretation of Cement Quality Logs

Keikha, Ali | 2022

282 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54839 (06)
  4. University: Sharif University of Technology
  5. Department: Chemical and Petroleum Engineering
  6. Advisor(s): Jamshidi, Saeed
  7. Abstract:
  8. The main responsibility of a primary cement job is to provide hydraulic isolation between various zones. Cement-sheath evaluation is concerned with the question of whether zonal isolation exists. Cement Evaluation Logs are used to evaluate the quality of cement sheath behind the casing or liner after cement job. these logs are a part of well integrity logs. Cement Evaluation Log results are complex and can be misunderstood, and it can lead to bad decisions that could have severe consequences. Cement evaluation logs must therefore be interpreted by experienced professionals. To help these interpreters, we propose a system for automatically interpreting cement evaluation logs, which they can use as a basis for their own interpretation. At first, we tried to interpret CBL individually by using explicit coding. We know that CBL works based on amplitude of first wave arrival that belongs to the casing. So, it cannot give us any information about relation of cement and formation. Therefore, we tried to interpret other logs like VDL in addition of CBL. In order to do that we used several machine learning methods. We compared these methods and chose the best model. It seems that Kernel SVM model has the best result on our dataset with accuracy of 93.1% on test set
  9. Keywords:
  10. Machine Learning ; Automatic Interpretation ; Well Integrity Management System ; Variable Density Log (VDL) ; Cement Bond Log (CBL) ; Cement Evaluation ; Cementing

 Digital Object List

 Bookmark

No TOC