No abstract

No abstract

Lost circulation is a serious problem that imposes some extra costs to petroleum and gas exploration operations. Substantial technical and economic benefits can be accomplished if the severity and frequency of mud loss are considered during the well planning procedure. This will lead to preventing the occurrence of losses by using treatments/solutions that are applied before entering lost circulation zones. In the present work, new models were developed to predict the amount of lost circulation using artificial neural networks (ANNs). This model was implemented to obtain a deeper understanding of the relations between the losses rate and the controllable drilling variables (i.e., rate of penetration [ROP], flow rate [FR], circulation pressure [CP], weight on bit [WOB], and rotation per minute [RPM]). The losses rate was found to be sensitive to high ROP, FR, and CP, such that increasing these parameters continuously increase the amount of lost circulation. While a slight rise in the losses rate was observed at high WOB and RPM. The proposed ANNs model was used to predict the losses rate for two wells, and comparison plot (actual amount of lost circulation versus predicted) was introduced as a function of depth. An accurate and early prediction of lost circulation has been of great importance to avoid the risks associated with this problem's occurrence.

The drill bit is the most essential tool in drilling operation and optimum bit selection is one of the main challenges in planning and designing new wells. Conventional bit selections are mostly based on the historical performance of similar bits from offset wells. In addition, it is done by different techniques based on offset well logs. However, these methods are time consuming and they are not dependent on actual drilling parameters. The main objective of this study is to optimize bit selection in order to achieve maximum rate of penetration (ROP). In this work, a model that predicts the ROP was developed using artificial neural networks (ANNs) based on 19 input parameters. For the modeling part, a one-dimension mechanical earth model (1D MEM) parameters, drilling fluid properties, and rig- and bit-related parameters, were included as inputs. The optimizing process was then performed to propose the optimum drilling parameters to select the drilling bit that provides the maximum possible ROP. To achieve this, the corresponding mathematical function of the ANNs model was implemented in a procedure using the genetic algorithm (GA) to obtain operating parameters that lead to maximum ROP. The output will propose an optimal bit selection that provides the maximum ROP along with the best drilling parameters. The statistical analysis of the predicted bit types and optimum drilling parameters comparing the actual flied measured values showed a low root mean square error (RMSE), low average absolute percentage error (AAPE), and high correction coefficient (R2). The proposed methodology provides drilling engineers with more choices to determine the best-case scenario for planning and/or drilling future wells. Meanwhile, the newly developed model can be used in optimizing the drilling parameters, maximizing ROP, estimating the drilling time, and eventually reducing the total field development expenses.

Stuck pipe is still a major operational challenge that imposes a significant amount of downtime and associated costs to petroleum and gas exploration operations. The possibility of freeing stuck pipe depends on response time and subsequent surface action taken by the driller during and after the sticking is experienced. A late and improper reaction not only causes a loss of time in trying to release stuck pipe but also results in the loss of an important portion of expensive tubular, downhole equipment and tools. Therefore, a fast and effective response should be made to release the stuck pipe. Investigating previous successful responses that have solved stuck pipe issues makes it possible to predict and adopt the proper treatments. This paper presents a study on the application of machine learning methodologies to develop an expert system that can be used as a reference guide for the drilling engineer to make intelligent decisions and reduce the lost time for each stuck pipe event. Field datasets, including the drilling operation parameters, formation type, and fluid mud characteristics, were collected from 385 wells drilled in Southern Iraq from different fields. The new models were developed to predict the stuck pipe solution for vertical and deviated wells using artificial neural networks (ANNs) and a support vector machine (SVM). The results of the analysis have revealed that both ANNs and SVM approaches can be of great use, with the SVM results being more promising. These machine learning methods offer insights that could improve response time and strategies for treating stuck pipe.