Selected article for: "decision tree and random forest"
Author: Nascimento, João; Maitelli, André; Maitelli, Carla; Cavalcanti, Anderson
Title: Diagnostic of Operation Conditions and Sensor Faults Using Machine Learning in Sucker-Rod Pumping Wells
  • Cord-id: 6naugkmz
  • Document date: 2021_7_2
    • ID: 6naugkmz
    Snippet: In sucker-rod pumping wells, due to the lack of an early diagnosis of operating condition or sensor faults, several problems can go unnoticed. These problems can increase downtime and production loss. In these wells, the diagnosis of operation conditions is carried out through downhole dynamometer cards, via pre-established patterns, with human visual effort in the operation centers. Starting with machine learning algorithms, several papers have been published on the subject, but it is still com
    Document: In sucker-rod pumping wells, due to the lack of an early diagnosis of operating condition or sensor faults, several problems can go unnoticed. These problems can increase downtime and production loss. In these wells, the diagnosis of operation conditions is carried out through downhole dynamometer cards, via pre-established patterns, with human visual effort in the operation centers. Starting with machine learning algorithms, several papers have been published on the subject, but it is still common to have doubts concerning the difficulty level of the dynamometer card classification task and best practices for solving the problem. In the search for answers to these questions, this work carried out sixty tests with more than 50,000 dynamometer cards from 38 wells in the Mossoró, RN, Brazil. In addition, it presented test results for three algorithms (decision tree, random forest and XGBoost), three descriptors (Fourier, wavelet and card load values), as well as pipelines provided by automated machine learning. Tests with and without the tuning of hypermeters, different levels of dataset balancing and various evaluation metrics were evaluated. The research shows that it is possible to detect sensor failures from dynamometer cards. Of the results that will be presented, 75% of the tests had an accuracy above 92% and the maximum accuracy was 99.84%.

    Search related documents:
    Co phrase search for related documents
    • acceptable accuracy and accuracy rate: 1
    • acceptable accuracy and accuracy value: 1
    • acceptable accuracy and logistic regression: 1
    • acceptable accuracy and low performance: 1
    • acceptable accuracy and machine learning: 1, 2, 3, 4, 5, 6, 7
    • acceptable accuracy and machine learning model: 1
    • acceptable accuracy and machine learning technique: 1
    • accuracy addition and logistic regression: 1
    • accuracy addition and machine learning: 1, 2, 3, 4, 5, 6, 7
    • accuracy equation and logistic regression: 1
    • accuracy obtain and logistic regression: 1
    • accuracy obtain and machine learning: 1, 2, 3, 4
    • accuracy obtain and machine learning apply: 1
    • accuracy obtain and machine learning model: 1