Abstract

Abstract Lost circulation is a very expensive drilling problem and very common in highly permeable formations, fractured formations or depleted reservoirs. Estimates of annual cost worldwide for lost circulation are over a billion for lost time and materials, and remediation costs. The drilling industry has a large toolbox from which to customize lost circulation responses. However, putting a value on the effectiveness of these lost circulation mitigation methods is harder to quantify. The Rumaila field, Iraq, is one of the world's largest oilfields with overlying formations that are notorious for lost circulation issues as the formations are depleted, highly permeable and fractured. Because of the significance of the Rumaila field and the common lost circulation problems faced in drilling any well in the area, it is an ideal candidate for a statistical study to model anticipated mud losses and compare the model with actual mud losses. The resulting model should be able to predict average mud losses, along with other drilling parameters affecting lost circulation, and compare the different lost circulation methods used to mitigate known losses. This study provides a larger data set and different models, using a machine learning algorithm than previous studies in the Rumaila field. Data of key drilling parameters for more than 500 wells are gathered from daily drilling reports, technical reports, final wells reports, and drilling programs. Sensitivity analysis identified the most critical parameters and provides insight into the impact of those parameters on mitigating lost circulation. The models of mud loss, equivalent circulating density (ECD) and drilling rate (ROP) are then tested with new data and compared with previous regression models developed for the area. Using the same techniques, modeling of any formation can be used to analyze the current situation and develop techniques for mitigating lost circulation by controlling drilling fluid properties, the rate of penetration, response to lost circulation events, and other field parameters.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.