Diagnostic of Operation Conditions and Sensor Faults Using Machine Learning in Sucker-Rod Pumping Wells.

João Nascimento,André Maitelli,Carla Maitelli,Anderson Cavalcanti

doi:10.3390/s21134546

Abstract

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%.

Highlights

In the search for answers to these questions, this paper presents results for several configurations, several ML algorithms, different balanced and imbalanced sets, the tuning of hyperparameters, and the use of automated machine learning (AutoML)
Procedures for tuning hyperparameters and pipelines generated by automated machine learning (AutoML) were tested
The results demonstrated that from a training dataset with many instances, good ML algorithms can produce high accuracy rates in the classification process

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Wells produce oil through natural lift (flowing) when the reservoir has enough energy to lift fluids to the surface with commercially successful flow rates. When the reservoir pressure is not sufficient to overcome the sum of the pressure losses along the fluid path to the tanks, there is a need for the supplementation of energy to the reservoir through artificial lift methods. There are several methods of artificial lift and these are generally divided into two basic groups: pneumatic methods and pumping methods

Methods

Results

Discussion

Conclusion