Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
The oil and gas industry pushes for longer, faster, and more reliable well construction. Predicting and optimizing drill bit performance offers tremendous potential to achieve high rate-of-penetrations. Torsional and lateral vibrations are detrimental to bits and drilling tools. Specifically, High-Frequency Torsional Oscillations (HFTO) can lead to electronic failures, body cracks and twist-offs of drilling tools. A recently upgraded full-scale drilling rig enables the analysis of drilling speed and generated high frequency vibrations under laboratory conditions. This paper presents new methods to optimize bit performance and stability fast, at low costs and low risks for performance and stability in a controlled environment. The results are validated by field operations in North America Land. Four bit designs were used to drill rocks under realistic downhole pressure and WOB and RPMs in the lab. High-frequency sensors at the rig and in the bit capture the rate-of-penetration and the dynamic response at multiple combinations of operative parameters. The data allow a full assessment of the performance, efficiency and lateral and torsional stability of bits using stability-maps, Rate of Penetration (ROP)-maps, MSE maps and Depth-of-Cut (DOC)-WOB curves. The lab tests are supported by 3D full bit simulations. The lab results are compared to field operations in vibration prone rocks in North America. The field runs were drilled in comparable well paths, formations and BHAs enabling a direct comparison. The bottom-hole-assemblies (BHA) were simulated and compared to high-frequency downhole data, surface data and offset-wells. Recommendations for choice and operation of the drill bits are deduced to reduce loads on the BHA while increasing drilling performance. The best bit design showed a 33% higher ROP while increasing the torsional stability. Stability maps revealed stable regions of RPM-WOB combinations free of torsional vibrations. HFTO can be mitigated by increasing the rotational speed above an RPM threshold. The range of HFTO free operative parameters was enlarged by 40% through bit design optimization. The best bit design also showed superior performance in the field achieving instantaneous ROP of more than 1,000 ft/h. Multiple record runs have been achieved with this frame including the most recent of drilling greater than 12,000 ft in a 24-hour period and drilling more than 25,000 feet in a single run. The new bit optimization methods enable to improve bit designs, develop operational recommendations quicker, minimize costs, and deliver more precise and reliable solutions compared to optimizations in field operations. Improvements of the performance and the torsional stability simultaneously are made possible through the upgraded drilling rig. The suppression of HFTO by bit design and cutter configuration combined with expanded stable operating parameters will lead to increased tool reliability, less NPT and higher drilling performance.
The oil and gas industry pushes for longer, faster, and more reliable well construction. Predicting and optimizing drill bit performance offers tremendous potential to achieve high rate-of-penetrations. Torsional and lateral vibrations are detrimental to bits and drilling tools. Specifically, High-Frequency Torsional Oscillations (HFTO) can lead to electronic failures, body cracks and twist-offs of drilling tools. A recently upgraded full-scale drilling rig enables the analysis of drilling speed and generated high frequency vibrations under laboratory conditions. This paper presents new methods to optimize bit performance and stability fast, at low costs and low risks for performance and stability in a controlled environment. The results are validated by field operations in North America Land. Four bit designs were used to drill rocks under realistic downhole pressure and WOB and RPMs in the lab. High-frequency sensors at the rig and in the bit capture the rate-of-penetration and the dynamic response at multiple combinations of operative parameters. The data allow a full assessment of the performance, efficiency and lateral and torsional stability of bits using stability-maps, Rate of Penetration (ROP)-maps, MSE maps and Depth-of-Cut (DOC)-WOB curves. The lab tests are supported by 3D full bit simulations. The lab results are compared to field operations in vibration prone rocks in North America. The field runs were drilled in comparable well paths, formations and BHAs enabling a direct comparison. The bottom-hole-assemblies (BHA) were simulated and compared to high-frequency downhole data, surface data and offset-wells. Recommendations for choice and operation of the drill bits are deduced to reduce loads on the BHA while increasing drilling performance. The best bit design showed a 33% higher ROP while increasing the torsional stability. Stability maps revealed stable regions of RPM-WOB combinations free of torsional vibrations. HFTO can be mitigated by increasing the rotational speed above an RPM threshold. The range of HFTO free operative parameters was enlarged by 40% through bit design optimization. The best bit design also showed superior performance in the field achieving instantaneous ROP of more than 1,000 ft/h. Multiple record runs have been achieved with this frame including the most recent of drilling greater than 12,000 ft in a 24-hour period and drilling more than 25,000 feet in a single run. The new bit optimization methods enable to improve bit designs, develop operational recommendations quicker, minimize costs, and deliver more precise and reliable solutions compared to optimizations in field operations. Improvements of the performance and the torsional stability simultaneously are made possible through the upgraded drilling rig. The suppression of HFTO by bit design and cutter configuration combined with expanded stable operating parameters will lead to increased tool reliability, less NPT and higher drilling performance.
Data is one of the most important limiting factors of deep machine learning (ML) model in drilling applications. Though a big size of historical data can be available, high-quality cleaned and labeled data is usually limited. In this case study, we show that with limited labeled data, physics-based data augmentation combined with unsupervised learning significantly improves both stability and accuracy in bit wear ML model. It provides a pathway to overcome labeled data shortage and field data quality limitations. Labeled bit wear data is usually limited because only the final bit dull state can be labeled using dull photos for the entire drilling distance. To overcome this difficulty, an encoder-decoder unsupervised ML framework based on Bi-directional LSTM architecture is first applied to the data of entire drilling distance to extract and maximize data learnings. Then, a physics-based wear estimator is implemented in the learned latent space to augment labeled wear dataset, guided by true wear labels and offset-well data. Weighting factor in loss function is applied to optimize augmented and true datasets in final supervised learning step. The proposed real-time bit wear model is built on a combination of physics-based data augmentation and unsupervised data learning method. The model is applied on multiple field bit runs. Results show that by implementing the unsupervised data learnings only, the prediction accuracy is improved by 30% compared to the baseline ML model. By combining physics-based augmentation, the accuracy is further improved by 10%. More importantly, adding physics-based data augmentation significantly reduces prediction variance and unphysical wear outputs, therefore improving prediction stability by more than 30%. It should be noted that the prediction stability of AI/ML model is crucial in real-time application and decision making. The results show physics-based data augmentation not only increases the size of label dataset and prevents model overfitting, but also applies physics-based guidance to the ML model effectively. It is learned weighting factor plays a crucial role in balancing loss contributions from true wear labels and physics-based labels. While low weighting factor of physics-based labels diminishes the augmented data, high weighting factor disrespects the true wear labels leading to a high prediction bias. Overall, the bit wear model study shows physic-based data augmentation combined with unsupervised data learning can effectively improve model accuracy, stability, and overcome labeled data shortage difficulty. The proposed paper shows a case study for the bit wear ML model using a combination of physics-based data augmentation and unsupervised data learning. While labeled data is one of the major challenges of ML models in many drilling applications, this study provides a pathway to improve both accuracy and stability of deep ML models with limited labeled data.
In-bit sensing technology measures the dynamic response at the bit during drilling operations. Recently such devices have been equipped with high sampling rate sensors, advanced sensor designs, and large data storage allowing entire bit runs to be recorded. This paper will present the technology, research, and testing that has allowed the development of a data driven decision loop for the optimization of drilling operations in the field. Data from the in-bit sensors allows the identification of drilling dysfunctions and provides actionable information from which to tailor drilling parameters to specific geologies. Additionally, drilling simulator testing, with in-bit sensors, in various geologies and with BHAs provides a database from which it is possible to create stability maps and bit performance benchmarks that can be directly used for optimization of drilling operations. Various drilling dysfunctions, such as High Frequency Torsional Oscillation (HFTO), are detrimental to both drilling efficiency and the reliability of downhole equipment. Drilling performance also varies by geologic features. Field case studies of the successful use of this technology in actual drilling operations will be presented to demonstrate the utility and impact of this technology. The data from these sensors is particularly useful due to their placement in the drill bit, where the fullest extent of downhole dynamic regimes can be observed. In bit sensors are showing utility in bit design, drilling optimization, and even well and field designs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.