Skip to content
Brasão da PUC-Rio
  • Home
  • About
  • Vice-Rectory for Development and Innovation Affairs
  • For Industry
  • Available Technologies
  • News
  • Contact
Menu
  • Home
  • About
  • Vice-Rectory for Development and Innovation Affairs
  • For Industry
  • Available Technologies
  • News
  • Contact
Linkedin-in Instagram Youtube Facebook-f
  • PortuguêsPT

Available Technologies

Cement analysis in oil wells with artificial intelligence

  • Engineering, Oil and gas, Software, Utilities

Increased reliability

The method is able to detect and estimate the severity of defects in the cement layer with high precision, reducing the risk of failures and leaks.

Cost savings

Automating cement analysis can reduce the costs of well abandonment operations.

Improved efficiency

The method is faster and more efficient than traditional analysis by human experts.

The problem-solution approach

Assessing the integrity of the cement layer in oil wells is an essential task to ensure the safety and longevity of the wells. However, the traditional analysis of this layer is carried out by human experts, who are subject to errors and delays in well abandonment operations.

What is it?

The invention proposed in this document is an innovative method for analyzing cement in oil wells that uses artificial intelligence (AI) and image processing techniques. The method is capable of automatically detecting and estimating the severity of defects in the cement layer with high precision.

How it works

The proposed method consists of converting acoustic profiling data into images. These images are then processed by an AI model trained to identify patterns that indicate the presence of defects in the cement layer.

Inventors

Alan Conci Kubrusly

Arthur Martins Barbosa Braga

Guilherme Rezende Bessa Ferreira

Helon Vicente Hultmann Ayala

João Humberto Guandalini Batista

Mateus Gheorghe De Castro Ribeiro

Roberth Waldo Angulo Llerena

Patent title:
Method for evaluating defects in the cement layer of wells based on image processing originating from profiling and aided by machine learning

Deposit Number:
BR 10 2022 014686 1

Share
Brasão da PUC-Rio
Home
A AgI
Vice-rectory
Available Technologies
For industry
News

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

Contact us

Phone:
+55 (21) 3527-2155

Useful links
Privacy policy