No abstract

Polymer degradation during Enhanced Oil Recovery (EOR) can have large impact on recovery rates during polymer flooding. In the field, few practical solutions exist to perform quality control/assurance (QA/QC) on EOR polymer fluids at surface and no solutions exist for measurements downhole. Here, we present the development of a miniaturized sensor that can be used to detect the onset of polymer degradation by measuring the viscous properties of EOR polymer fluids. The device was tested on samples collected from a polymer flooding operation. We describe its integration into wellsite portable systems and into an untethered logging tool for cost-effective routine measurements downhole. The sensors are based on millimeter-sized piezoelectric tuning fork resonators. The viscosity and density of the fluids was measured from the energy dissipation and the resonant frequency obtained from their vibrational spectra. The devices were specially designed for use in high-salinity polymer fluids. They were tested and validated on samples collected from a single well polymer flood trial. A miniaturized electrical measurement platform was then designed for use at surface in the field and for use in a compact untethered logging tool for quick and inexpensive deployment downhole. The devices were initially calibrated in the laboratory and then tested on samples collected from the field. These two field-collected solutions were used to preflush the formation before injecting surfactant-polymer solution and as a polymer taper to drive the injected surfactant-polymer solution, respectively. The obtained viscosity values correlated very well with those obtained from standard laboratory measurements. Therefore, the changes in viscosity due to reduction in the molecular weight of the polymer, as measured with the miniature devices, can be used to assess whether degradation has taken place. A miniaturized electrical measurement platform was then tested in comparable polymer fluids for use in the field and obtained comparable results. The platforms described here provide a simple, cost-effective, and user-friendly platform for the detection of polymer degradation in the field, thus providing valuable information in real-time during costly polymer flooding operations.

Objective/Scope. Lost circulation events (LCEs) are among the top causes for drilling nonproductive time (NPT). The presence of natural fractures and vugular formations causes loss of drilling fluid circulation. Drilling depleted zones with incorrect mud weights can also lead to drilling induced losses. LCEs can also develop into additional drilling hazards, such as stuck pipe incidents, kicks, and blowouts. An LCE is traditionally diagnosed only when there is a reduction in mud volume in mud pits in the case of moderate losses or reduction of mud column in the annulus in total losses. Using machine learning (ML) for predicting the presence of a loss zone and the estimation of fracture parameters ahead is very beneficial as it can immediately alert the drilling crew in order for them to take the required actions to mitigate or cure LCEs. Methods, Procedures, Process. Although different computational methods have been proposed for the prediction of LCEs, there is a need to further improve the models and reduce the number of false alarms. Robust and generalizable ML models require a sufficiently large amount of data that captures the different parameters and scenarios representing an LCE. For this, we derived a framework that automatically searches through historical data, locates LCEs, and extracts the surface drilling and rheology parameters surrounding such events. Results, Observations, and Conclusions. We derived different ML models utilizing various algorithms and evaluated them using the data-split technique at the level of wells to find the most suitable model for the prediction of an LCE. From the model comparison, random forest classifier achieved the best results and successfully predicted LCEs before they occurred. The developed LCE model is designed to be implemented in the real-time drilling portal as an aid to the drilling engineers and the rig crew to minimize or avoid NPT. Novel/Additive Information. The main contribution of this study is the analysis of real-time surface drilling parameters and sensor data to predict an LCE from a statistically representative number of wells. The large-scale analysis of several wells that appropriately describe the different conditions before an LCE is critical for avoiding model undertraining or lack of model generalization. Finally, we formulated the prediction of LCEs as a time-series problem and considered parameter trends to accurately determine the early signs of LCEs.

No abstract

During drilling operations, measurements of drilling fluid/mud viscosity and density provide key information to ensure safe operations (e.g., maintain wellbore integrity) and improve the rate of penetration (e.g., maintain proper hole cleaning). Nowadays, these measurements are still performed manually by using a calibrated funnel viscometer and a weight balance, as stipulated by current American Petroleum Institute (API) standards. In this study, we introduce an automated viscosity/density measurement system based on an electromechanical tuning fork resonator. The system allows for continuous measurements as fast as several times per second in a compact footprint, allowing it to be deployed in tanks or pipelines and/or gathering data from multiple sensors in the mud circulation system. The streams of data produced were broadcasted to a nearby computer allowing for live monitoring of the viscosity and density. The results obtained by the in-tank system in five wells were in good agreement with the standard reference measurements from the mud logs. Here, we describe the development and testing of the tool as well as general guidelines for integration into a rig edge-computing system for real-time analytics and detection of operational problems and drilling automation.