Analyzing the integrity of the cement layer in oil wells is a complex and subjective task that requires experts to interpret large amounts of data. This task is susceptible to human error and can lead to delays and additional costs in well abandonment operations.
The data analysis platform proposed in this patent uses machine learning techniques to help experts interpret acoustic profiling data. The proposed method reduces analysis time, increases the reliability of assessments and provides improved data visualization.
The platform consists of software that receives acoustic profiling data as input. The software uses machine learning techniques to identify patterns in the data that may indicate the integrity of the cement layer. The results of the analysis are presented to the expert in an intuitive graphical interface, which makes it easier to understand the data and make decisions.
Patent title:
Computer platform with graphical interface based on active machine learning for the visualization, inference and assisted interpretation of data obtained in cement profiling operations in oil and gas wells and method of its use
Deposit Number:
BR 10 2022 014688 8
Pontifical Catholic University of Rio de Janeiro – PUC-Rio
Rua Marquês de São Vicente, 225, Gávea
Rio de Janeiro, RJ – Brasil
Zip code: 22451-900
Postal box: 38097
Phone:
+55 (21) 3527-2155