Drilling in the Fourth Industrial Revolution—Vision and Challenges

Gooneratne, Chinthaka P.; Magana-Mora, Arturo; Otalvora, William Contreras; Affleck, Michael; Singh, Pratyush; Zhan, Guo‐Dong; Moellendick, Timothy

doi:10.1109/emr.2020.2999420

Cited by 44 publications

(9 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although several studies using computational models have been proposed for the prediction and detection of multiple drilling applications [3][4][5][6], only a few studies have focused on the applications of ML in drilling fluids analysis. Among these studies, Gowida et al [7] proposed a data-driven framework to predict the rheological properties of a specific drilling fluid formulations type, which is the CaCl2 brine-based drill-in fluid.…”

Section: Related Workmentioning

confidence: 99%

Drilling Fluid Properties Prediction: A Machine Learning Approach to Automate Laboratory Experiments

Aljubran

AlBahrani

Ramasamy

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Providing access to underground energy resources such as oil, gas, and geothermal energy requires drilling through subterranean rock formations. Drilling fluids are commonly used to enable this drilling process by serving a variety of functions. Chief among these is circulating into the drilled wellbore to remove the produced rock cuttings. Other functions include exerting the hydrostatic pressure necessary to prevent the flow of underground fluids into the wellbore while drilling, minimizing the invasion of solids and undesired fluids into the wellbore rock, and ensuring the fluid remains flowable within the means of the pumps available on site. To assess the ability of a drilling fluid to serve these functions, it has to have certain rheological properties, which are conventionally measured using specialized equipment. Considering that the formulation and components of these drilling fluids can vary greatly for different scenarios, the process of preparing samples and measuring their rheological properties, which is usually performed on a daily basis on a drilling site, is unavoidably time-consuming, repetitive, and error-prone. Based on this, it is apparent that there is a need for a computational model that can accurately predict drilling fluids properties based on the proposed concentration of their components without the need for further laboratory testing. This study describes a novel methodology to train a machine learning model derived from over 6,878 drilling fluid formulations to successfully predict water-based drilling fluids properties with a resulting R2 of 91.07 ± 6.35%.

show abstract

Section: Related Workmentioning

confidence: 99%

Drilling Fluid Properties Prediction: A Machine Learning Approach to Automate Laboratory Experiments

Aljubran

AlBahrani

Ramasamy

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These sources or sensors could also belong to different drilling rig contractors and service providers who collaborate to complete a variety of tasks and operations. As a result, drilling databases host a collection of records stemming from multiple sources, which results in asynchronous data (the clock in every microcontroller is slightly different) and potentially inconsistent sensor sampling frequency [28,29]. Whereas these problems could be resolved or alleviated by transmitting a common pulse to sensors to collect records simultaneously, this is not a standard practice in drilling operations.…”

Section: B Literature Reviewmentioning

confidence: 99%

Deep Learning and Time-Series Analysis for the Early Detection of Lost Circulation Incidents During Drilling Operations

et al. 2021

Self Cite

View full text Add to dashboard Cite

Drilling operations consist of breaking the rock to deepen a wellbore for oil or gas extraction. A drilling fluid, circulating from the surface through the drill pipe and from the annulus to the surface, is used to remove rock cuttings and maintain hydrostatic pressure. Drilling fluid lost circulation incidents (LCIs) are major sources of non-productive time (NPT) in drilling operations. These incidents occur due to preexisting natural fractures (vugs, caverns, etc.) and/or drilling-induced hydraulic fractures. The initiation of an LCI could lead to other hazardous drilling phenomena, such as formation influx or kick/blowout, stuck pipe incidents, among others. LCIs are typically monitored at the rig site by observing drilling fluid levels in the fluid tanks. This manual process incurs missing the occurrence or late detection of LCIs. Machine learning (ML) and deep learning (DL) classification algorithms are powerful in processing time-series data and achieving early detection of such temporal phenomena. In this study, we performed a large-scale analysis of the surface drilling and rheology data obtained from historical wells with LCIs. This analysis includes primary and secondary preprocessing steps including, aggressive sampling, feature engineering, and window normalization to derive generalizable DL models for real-time operations. Focal loss was utilized to account for data class imbalance and train robust and generalizable models. The results obtained from different ML/DL algorithms showed that one-dimensional convolutional neural network models resulted in the best performance with state-of-the-art precision, recall, and F1 scores of 87.34%, 73.40%, and 79.77%, respectively, on unseen test drilling data.

show abstract

“…Even oil pipelines and energy infrastructure are not immune as evidenced by recent cyber-attacks on major pipeline control systems [19], [20]. The advantages of Industry 4.0 and other advanced digital technologies, such as 5G and blockchain technology, have appeared in the pages of EMR [21], [22].…”

Section: Supporting a Resilience And Recovery Ecosystem Through Cybersecurity Innovationmentioning

confidence: 99%

Enhancing a Resilience and Recovery Ecosystem Through Innovation—Doing Our Part

Sarkis

2021

IEEE Eng. Manag. Rev.

View full text Add to dashboard Cite

Drilling in the Fourth Industrial Revolution—Vision and Challenges

Cited by 44 publications

References 64 publications

Drilling Fluid Properties Prediction: A Machine Learning Approach to Automate Laboratory Experiments

Drilling Fluid Properties Prediction: A Machine Learning Approach to Automate Laboratory Experiments

Deep Learning and Time-Series Analysis for the Early Detection of Lost Circulation Incidents During Drilling Operations

Enhancing a Resilience and Recovery Ecosystem Through Innovation—Doing Our Part

Contact Info

Product

Resources

About