Tool manufacturers have made significant progress improving downhole drilling technologies, but little effort has focused on optimizing the drilling process. The set-it-and-forget-it approach and inherent inefficiencies of the automatic driller are inadequate for keeping bit parameters matched to lithology and wellbore conditions. The industry requires a new methodology to help rig-site personnel make informed drilling parameter decisions based on real-time offset data analysis that increases operating efficiency to reduce drilling costs.To solve the problem an artificial neural network (ANN) drilling parameter optimization system was developed to provide rig-site personnel real-time information to ensure maximum run length from all bits and downhole tools at the highest possible ROP. Benefits of the new system include extended tool life, fewer trips and the ability to manage the bits dull condition.The objective is to replace the human factor of applying operating parameters such as WOB and RPM with the intelligent ANN learned experience. Using the ANN software system, operating parameters can be selected based on the documented physical rock characteristics (offset log data) of formations being penetrated and then fine tuned for the bits specific cutting structure and wear rate. By following the real-time ANN recommendations, changes can be implemented to increase overall ROP while maximizing bit life by managing the dull condition.The overall project results were positive and proved successful in all the trails carried out after this field trial. This paper will address the methodology of the new approach and highlight the importance of planning and implementing the drilling parameters in realtime.
Accurately predicting the rate of penetration (ROP) is a prominent factor affecting economic and engineering decisions during well planning. However, ROP prediction based on simple algorithms applied to offset wells has historically yielded mixed results. To improve ROP predicting capabilities, the provider is applying an artificial neural network (ANN) to analyze offset drilling data. The system has significantly improved the ability to accurately predict drilling performance, despite expected changes in lithology, hole size, bit type and mud properties. The flexibility of the software package allows engineers to analyze a wide range of information and deliver high-quality ROP predictions based on previous experience and data from offset wells. The process includes detail scrutiny of the offset and training of the ANN system until the neural network is validated. The simulation is then run to solve expected ROP, using any changed drilling conditions as input. In a recent case, an operator required a well that would have to be drilled deeper than offsets and with different borehole sizes. By applying the neural network capabilities, engineers were able to deliver analytical ROP predictions for the planned well, including quality result for different lithologies with a wide range of rock strength values. This paper will focus on the new ANN technologies being utilized for predicting drilling performance. It will also include a case study that documents its successful application.
Tool manufacturers have made significant progress improving downhole drilling technologies, but little effort has focused on optimizing the drilling process. The set-it-and-forget-it approach and inherent inefficiencies of the automatic driller are inadequate for keeping bit parameters matched to lithology and wellbore conditions. The industry requires a new methodology to help rig-site personnel make informed drilling parameter decisions based on real-time offset data analysis that increases operating efficiency to reduce drilling costs. To solve the problem, the service provider launched an artificial neural network (ANN) drilling parameter optimization system (DBOS OnTime) which provides rig-site personnel real-time information to ensure maximum run length from all bits and downhole tools at the highest possible penetration rates (ROP). Benefits of the new system include extended tool life, fewer trips and the ability to manage the bit's dull condition. The objective is to replace the human factor of applying operating parameters such as weight on bit (WOB) and RPM with the intelligent ANN "learned experience." By using the ANN based software system, operating parameters can be selected based on the documented physical rock characteristics (offset log data) of the formations being penetrated and then fine tuned for the bit's specific cutting structure and wear rate. By following the real-time ANN recommendations, changes can be implemented to increase overall penetration rates (ROP) while maximizing bit life by managing the dull condition.
A well plan is essentially a decision-making roadmap for choosing equipment required for drilling the required wellbore. The operator's ability to properly assess offset drilling data and key lithology factors to match available BHA tools and procedures plays a large role in determining project success. Accordingly, the software support systems utilized to interpret and extrapolate data have a direct impact on the ability of drilling engineers to optimize operations. Historically, most well plans were assembled using data from offset wells and prior experience. However in most cases, a rudimentary analysis could not produce a comprehensive picture of the complex, interdisciplinary downhole dynamics that affect drilling performance, especially in the case of limited or missing offset data. Even when reliable data was available, a one-dimensional analysis has failed to completely exploit the available informational value from offset wells. This has forced engineers to be more conservative when designing wells and include more contingencies. The result is operators are drilling in a reactive manner, which often led to decisions resulting in performance degradation rather than optimization. To solve the problem and improve drilling performance in areas of limited/inaccurate offset data, engineers have developed a Mechanical Efficiency Ratio optimization system (MER) that accurately measures the BHA's use of available energy. The modeling tool was tested in several applications and accurately predicted performance including ROP, footage capabilities and dull bit condition. The tool used data and evaluation of rig capabilities, bit/BHA performance, downhole behavior and formation challenges including high-rock strength and interbedded lithologies. The authors will present three case studies that outline how the software program was used to measure system efficiency to determine which bit would have the highest ROP, total footage capabilities and best dull grade estimate compared to offset runs. The MER will also determine if the system (bit/BHA) or the optimized drilling parameters will improve drilling efficiency.
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
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.