Automatic Method for Anomaly Detection while Drilling

Golitsyna, Maria; Semenikhin, Artyom; Chebuniaev, I.; Vasilyev, Vladimir; Koryabkin, Vitaliy; Макаров, В. А.; Simon, Igor; Baybolov, Timur; Osmonalieva, Oksana Taalaevna

doi:10.3997/2214-4609.202032026

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through correlation analysis and mechanistic knowledge, parameters that have a greater impact on drilling conditions are selected, parameters that have less impact or are irrelevant are removed, the dimension of input parameters is reduced, and two or more parameters with high similarity are avoided at the same time. The Spearman correlation coefficient [16] is selected for analysis in this paper, and the calculation formula is shown in Equation (1). The specific calculation formula is as follows,…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…following are some shortcomings of SVM: (1) long training times for large datasets; (2) it is easily impacted by increased data noise.…”

Section: Stacking Ensemble Learning (Sel)mentioning

confidence: 99%

“…Golitsyna et al [1] proposed an automatic anomaly detection method during drilling, based on machine learning, which used drilling parameters to improve the intelligent detection effect of abnormal conditions in drilling.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Drilling Conditions Classification Based on Improved Stacking Ensemble Learning

Yang,

Zhang,

Zhou

et al. 2023

Energies

View full text Add to dashboard Cite

The classification of drilling conditions is a crucial task in the drilling process, playing a vital role in improving drilling efficiency and reducing costs. In this study, we propose an improved stacking ensemble learning algorithm with the objective of enhancing the performance of drilling conditions classification. Additionally, this algorithm aims to have a positive impact on automated drilling time estimation and the continuous improvement of efficiency. In our experimental setup, we employed various base learners, such as random forests, support vector machine, and the K-nearest neighbors algorithm, as initial models for the task of drilling conditions classification. To improve the model’s expressive power and feature relevance specifically for this task, we enhanced the meta-model component of the stacking algorithm by incorporating feature engineering techniques. The experimental results show that the improved ensemble learning algorithm achieves an accuracy and recall rate of 97% and 98%, respectively. Through continuous improvement in drilling operations, the average sliding time is reduced by 21.1%, and the average Rate of Penetration (ROP) is increased by 15.65%. This research holds significant importance for engineering practice in the drilling industry, providing robust support for optimizing and enhancing the drilling process.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

“…following are some shortcomings of SVM: (1) long training times for large datasets; (2) it is easily impacted by increased data noise.…”

Section: Stacking Ensemble Learning (Sel)mentioning

confidence: 99%

See 1 more Smart Citation

Drilling Conditions Classification Based on Improved Stacking Ensemble Learning

Yang,

Zhang,

Zhou

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

Performance evaluation of outlier detection techniques in production timeseries: A systematic review and meta-analysis

Alimohammadi

Chen

2022

Expert Systems with Applications

View full text Add to dashboard Cite

Exploration Drilling Management System Based on Digital Twins Technology

Kalinin

Elfimov

Baybolov

2021

Day 3 Thu, September 23, 2021

View full text Add to dashboard Cite

Digital transformation of oil and gas companies requires consistent improvement of work performance management. Oil and gas companies strive to improve work efficiency and consistently develop and implement digital products. The realization of such complicated solutions requires deep diving into current business processes and transformation of them. This paper deals with implementation of digital management system for exploration and production wells. Digital management system for exploration and production wells is based on ideology of digital twin and act as a single window and single source of data for all exploration and production wells. Digital management system covers whole construction process started from planning stage to execution and results assessment and orchestrates the exchange of data between process phases and people involved in it. Transparency provided by the digital twin improves efficiency and accelerates well construction process. Cognitive assistants based on AI and ML techniques are implemented at every stage: while planning, the assistants search analogue wells, analyze its design and complications while drilling and provide recommendations for the most optimal well design, offers the optimum drilling mud density and recommends the most suitable set of logs to cover geological section uncertainty. At the execution stage, a number of ML assistants are used to increase efficiency and reduce risks while drilling: automatic method for anomaly detection while drilling to prevent complications while drilling, machine learning based model for automatic torque and drag control to control borehole condition to predict any signs of differential stuck, key sitting and pack-off, data-driven model for drilling bit position and direction determination to predict BHA position while drilling including a blind zone, data-driven model for the identification of the rock type at a drilling bit for correct geosteering application.

show abstract

Automatic Method for Anomaly Detection while Drilling

Cited by 4 publications

References 0 publications

Drilling Conditions Classification Based on Improved Stacking Ensemble Learning

Drilling Conditions Classification Based on Improved Stacking Ensemble Learning

Performance evaluation of outlier detection techniques in production timeseries: A systematic review and meta-analysis

Exploration Drilling Management System Based on Digital Twins Technology

Contact Info

Product

Resources

About