Use of Radial Basis Function Networks for Efficient Well Production Allocation

Zubarev, Maxim; Zubarev, Denis Igorevich

doi:10.2118/198860-ms

Cited by 2 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tool has accomplished a good way of dealing with the high noise data during the model development . The transformation technique within the algorithm is a nonlinear relationship type linked to the weighting vector of the hidden layer and model optimization for reaching a high accuracy level during the prediction. − This processing layout is shown in Figure , which clarifies the RBF model used for modeling the vibration prediction.…”

Section: Data Description and Machine Learningmentioning

confidence: 99%

Machine Learning Solution for Predicting Vibrations while Drilling the Curve Section

Saadeldin,

Gamal,

Elkatatny

2023

ACS Omega

View full text Add to dashboard Cite

The downhole vibration is one of the most crucial factors that affect downhole equipment performance and failure, besides wellbore instability. Downhole tool failure, hole problems, mechanical energy loss, and ineffective drilling performance are commonly associated with drillstring high vibration levels. The high vibration level will lead to more complications while drilling that might cause nonproductive time and extra cost. Meanwhile, the downhole sensors for detecting the drillstring vibrations add more cost to the operation. Consequently, the new solutions based on technology capabilities provide a powerful tool to integrate and interpret the drilling data for the best use of @@the data for operation performance enhancement. This study provides a successful application for utilizing the surface drilling data to automate drillstring vibration detection during the drilling curve section employing machine learning (ML) techniques. The axial, torsional, and lateral vibration modes are detected through testing four ML techniques named the @@adaptive neuro-fuzzy inference system (ANFIS), radial basis function (RBF), functional networks (FN), and support vector machines (SVMs) with real field data. The models’ development was achieved by comprehensive study starting from data gathering, wrangling, statistical analysis, developing the ML models, evaluating the model prediction accuracy, and reporting the high accuracy results. The developed models were evaluated, and results showed that ANFIS and SVM models provided the highest accuracy with a coefficient of correlation (R) ranging from 0.9 to 0.99 followed by the RBF and FN models through model training and testing (R ranging from 0.82 to 0.96). Validating the models over unseen data confirmed the high accuracy prediction for the three vibration modes. Generally, the developed models provided technically accepted accuracy with R higher than 0.93 and AAPE less than 2.8% for SVM and ANFIS models while FN and RBF showed R between 0.82 and 0.95 and AAPE less than 5.7% between actual readings and predictions. Based on these results, the developed ML algorithm might be utilized as an intelligent solution to autodetect downhole vibration while drilling from surface sensor data only, which will save the downhole tool cost.

show abstract

Section: Data Description and Machine Learningmentioning

confidence: 99%

Machine Learning Solution for Predicting Vibrations while Drilling the Curve Section

Saadeldin,

Gamal,

Elkatatny

2023

ACS Omega

View full text Add to dashboard Cite

show abstract

Rig Sensor Data for AI-ML Technology-Based Solutions: Research, Development, and Innovations

Gamal,

Elkatatny,

Al Gharbi

2023

Day 2 Tue, October 03, 2023

View full text Add to dashboard Cite

The oil and gas industry is currently witnessing a notable shift towards automation and digitalization, driven by cutting-edge technologies like artificial intelligence (AI), machine learning (ML), the Internet of Things (IoT), and big data analytics. These advanced solutions are being implemented to enhance operational efficiency, improve profitability, and enable data-driven decision-making. Among the various segments of the petroleum industry, drilling operations for oil and gas wells hold immense significance due to the high sharing of the total well cost. Therefore, the adoption of technology-driven solutions is crucial to ensure safe operations and cost reduction. This paper presents the successful applications overview of machine learning in the drilling operations domain and addresses the existing challenges and future opportunities in this field. Surface drilling sensors record real-time drilling parameters such as weight on bit, hook load, drill string rotation, drilling torque, pumping rate and pressure, and rate of penetration. These drilling data parameters provide valuable information about the characteristics of the drilled rock, requiring appropriate preprocessing techniques for data quality improvement. Data collection, preprocessing, analysis, and the development of machine learning models for prediction and classification in drilling operations are significant areas of research. Numerous researchers have utilized drilling data in machine learning applications to predict and optimize drilling rate, drill string vibrations, rock characteristics, and other important variables. These models contribute to optimizing drilling parameters, enhancing operational performance, and reducing costs. The paper technically discusses the achievements in ML research and industrial applications within the drilling domain that cover various ML techniques, different data sources, diverse training data for model features, and the target outputs from the developed models. The research findings highlight the exceptional performance of ML applications, technically and economically, by showcasing successful case studies from the industry. Through the analysis of observations, valuable recommendations and potential future opportunities have been identified. These findings open up promising avenues for improvement and development in various areas. ML applications in drilling data have significantly contributed to the industry and academia by enabling real-time monitoring, advisory systems, automation, digitalization, and accurate prediction and classification through developed ML models.

show abstract

Use of Radial Basis Function Networks for Efficient Well Production Allocation

Cited by 2 publications

References 29 publications

Machine Learning Solution for Predicting Vibrations while Drilling the Curve Section

Machine Learning Solution for Predicting Vibrations while Drilling the Curve Section

Rig Sensor Data for AI-ML Technology-Based Solutions: Research, Development, and Innovations

Contact Info

Product

Resources

About