Effectively transporting drilled cuttings to the surface is a vital part of the well construction process. Usually, mechanistic models are used to estimate the cuttings concentration during drilling. Based on the results from these model, operational parameters are adjusted to mitigate any nonproductive time events such as pack-off or lost circulation. However, these models do not capture the underlying complex physics completely and frequently require updating the input parameters, which is usually performed manually. To address this, in this study, a data-driven modeling approach is taken and evaluated together with widely used mechanistic models. Artificial neural networks are selected after several trials. The experimental data collected at The University of Tulsa–Drilling Research Projects (in the last 40 years) are used to train and validate the model, which includes a wide range of wellbore and pipe sizes, inclinations, rate-of-penetration values, pipe rotation speeds, flow rates, and fluid and cuttings properties. It is observed that, in many cases, the data-driven model significantly outperforms the mechanistic models, which provides a very promising direction for real-time drilling optimization and automation. After the neural network is proven to work effectively, an optimization attempt to estimate flow rate and pipe rotation speed is introduced using a genetic algorithm. The decision is made considering minimizing the required total energy for this process. This approach may be used as a design tool to identify the required flow rate and pipe rotation speed to acquire effective hole cleaning while consuming minimal energy.
Drilling practice has been evolving parallel to the developments in the oil and gas industry. Current supply and demand for oil and gas dictate search for hydrocarbons either at much deeper and hard-to-reach fields, or at unconventional fields, both requiring extended reach wells, long horizontal sections, and 3D complex trajectories. Cuttings transport is one of the most challenging problems while drilling such wells, especially at mid-range inclinations. For many years, numerous studies have been conducted to address modeling of cuttings transport, estimation of the concentration of cuttings as well as pressure losses inside the wellbores, considering various drilling variables having influence on the process. However, such attempts, either mechanistic or empirical, have many limitations due to various simplifications and assumptions made during the development stage. Fluid thixotropy, temperature variations in the wellbore, uncertainty in pipe eccentricity as well as chaotic motion of cuttings due to pipe rotation, imperfections in the wellbore walls, variations in the size and shape of the cuttings, presence of tool joints on the drillstring, etc. causes the modeling of the problem extremely difficult. Due to the complexity of the process, the estimations are usually not very accurate, or not reliable. In this study, data-driven models are used to address the estimation of cuttings concentration and frictional loss estimation in a well during drilling operations, instead of using mechanistic or empirical methods. The selected models include Artificial Neural Networks, Random Forest, and AdaBoost. The training of the models is determined using the experimental data regarding cuttings transport tests collected in the last 40 years at The University of Tulsa – Drilling Research Projects, which includes a wide range of wellbore and pipe sizes, inclinations, ROPs, pipe rotation speeds, flow rates, fluid and cuttings properties. The evaluation of the models is conducted using Root Mean Square Error, R-Squared Values, and P-Value. As the inputs of the data-driven models, independent drilling variables are directly used. Also, as a second approach, dimensionless groups are developed based on these independent drilling variables, and these dimensionless groups are used as the inputs of the models. Moreover, performance of the data-driven model results are compared with the results of a conventional mechanistic model. It is observed that in many cases, data-driven models perform significantly better than the mechanistic model, which provides a very promising direction to consider for real time drilling optimization and automation. It is also concluded that using the independent drilling variables directly as the model inputs provided more accurate results when compared with dimensional groups are used as the model inputs.
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.