Realtime Rate of Penetration Optimization Using the Shuffled Frog Leaping Algorithm
01 May 2015-Journal of Energy Resources Technology-transactions of The Asme (American Society of Mechanical Engineers)-Vol. 137, Iss: 3, pp 032902
TL;DR: The metaheuristic evolutionary algorithm, called the “shuffled frog leaping algorithm,” (SFLA) is used in this paper, a type of rising swarm-intelligence optimizer that can optimize additional objectives, such as minimizing hydromechanical specific energy.
Abstract: The increasing complexities of wellbore geometry imply an increasing well cost. It has become more important than ever to achieve an increased rate of penetration (ROP) and, thus, reduced cost per foot. To achieve maximum ROP, an optimization of drilling parameters is required as the well is drilled. While there are different optimization techniques, there is no acceptable universal mathematical model that achieves maximum ROP accurately. Usually, conventional mathematical optimization techniques fail to accurately predict optimal parameters owing to the complex nature of downhole conditions. To account for these uncertainties, evolutionary-based algorithms can be used instead of mathematical optimizations. To arrive at the optimum drilling parameters efficiently and quickly, the metaheuristic evolutionary algorithm, called the “shuffled frog leaping algorithm,” (SFLA) is used in this paper. It is a type of rising swarm-intelligence optimizer that can optimize additional objectives, such as minimizing hydromechanical specific energy. In this paper, realtime gamma ray data are used to compute values of rock strength and bit–tooth wear. Variables used are weight on bit (WOB), bit rotation (N), and flow rate (Q). Each variable represents a frog. The value of each frog is derived based on the ROP models used individually or simultaneously through iteration. This optimizer lets each frog (WOB, N, and Q) jump to the best value (ROP) automatically, thus arriving at the near optimal solution. The method is also efficient in computing optimum drilling parameters for different formations in real time. The paper presents field examples to predict and estimate the parameters and compares them to the actual realtime data.
Citations
More filters
TL;DR: In this paper, the simultaneous effect of six variables on penetration rate using real field drilling data has been investigated, and the bat algorithm was used to identify optimal range of factors in order to maximize drilling rate of penetration.
80 citations
TL;DR: To predict penetration rate during drilling process, several ANN models were developed based on the data obtained from drilling of a gas well located in south of Iran and showed that the best model was selected for prediction of penetration rate.
Abstract: Predictive models have been widely used in different engineering fields, as well as in petroleum engineering. Due to the development of high-performance computer systems, the accuracy and complexity of predictive models have been increased significantly. One of the common methods for prediction is artificial neural network (ANN). ANN models in combination with optimization algorithms provide a powerful and fast tool for the prediction and optimization of processes which take a large amount of time if they are simulated using common simulation technics. In the present paper, to predict penetration rate during drilling process, several ANN models were developed based on the data obtained from drilling of a gas well located in south of Iran. Regarding the R2 and RMSE values of the developed models, the best model was selected for prediction of penetration rate. In the next step, artificial bee colony algorithm was used for optimization of the parameters which are effective on rate of penetration (ROP). Results showed that the model is accurate enough for being used in the prediction and optimization of ROP in drilling operations.
56 citations
TL;DR: In this paper, a new robust model was introduced to predict the rate of penetration (ROP) using both drilling parameters (WOB, Q, ROP, torque (T), standpipe pressure (SPP), uniaxial compressive strength (UCS), and mud properties (density and viscosity) using 7000 real-time data measurements.
Abstract: During the drilling operations, optimizing the rate of penetration (ROP) is very crucial, because it can significantly reduce the overall cost of the drilling process. ROP is defined as the speed at which the drill bit breaks the rock to deepen the hole, and it is measured in units of feet per hour or meters per hour. ROP prediction is very challenging before drilling, because it depends on many parameters that should be optimized. Several models have been developed in the literature to predict ROP. Most of the developed models used drilling parameters such as weight on bit (WOB), pumping rate (Q), and string revolutions per minute (RPM). Few researchers considered the effect of mud properties on ROP by including a small number of actual field measurements. This paper introduces a new robust model to predict the ROP using both drilling parameters (WOB, Q, ROP, torque (T), standpipe pressure (SPP), uniaxial compressive strength (UCS), and mud properties (density and viscosity) using 7000 real-time data measurements. In addition, the relative importance of drilling fluid properties, rock strength, and drilling parameters to ROP is determined. The obtained results showed that the ROP is highly affected by WOB, RPM, T, and horsepower (HP), where the coefficient of determination (T2) was 0.71, 0.87, 0.70, and 0.92 for WOB, RPM, T, and HP, respectively. ROP also showed a strong function of mud fluid properties, where R2 was 0.70 and 0.70 for plastic viscosity (PV) and mud density, respectively. No clear relationship was observed between ROP and yield point (YP) for more than 500 field data points. The new model predicts the ROP with average absolute percentage error (AAPE) of 5% and correlation coefficient (R) of 0.93. In addition, the new model outperformed three existing ROP models. The novelty in this paper is the application of the clustering technique in which the formations are clustered based on their compressive strength range to predict the ROP. Clustering yielded accurate ROP prediction compared to the field ROP.
50 citations
TL;DR: In this article, an artificial neural network (ANN) model to predict hydraulics was implemented through the fitting tool of matlab and the sensitivity analysis of input parameters on the created model was investigated by using forward regression method.
Abstract: Real-time drilling optimization improves drilling performance by providing early warnings in operation Mud hydraulics is a key aspect of drilling that can be optimized by access to real-time data. Different from the investigated references, reliable prediction of pump pressure provides an early warning of circulation problems, washout, lost circulation, underground blowout, and kicks. This will help the driller to make necessary corrections to mitigate potential problems. In this study, an artificial neural network (ANN) model to predict hydraulics was implemented through the fitting tool of matlab. Following the determination of the optimum model, the sensitivity analysis of input parameters on the created model was investigated by using forward regression method. Next, the remaining data from the selected well samples was applied for simulation to verify the quality of the developed model. The novelty is this paper is validation of computer models with actual field data collected from an operator in LA. The simulation result was promising as compared with collected field data. This model can accurately predict pump pressure versus depth in analogous formations. The result of this work shows the potential of the approach developed in this work based on NN models for predicting real-time drilling hydraulics.
50 citations
TL;DR: It is concluded that data-driven models can be used for real-time drilling despite their computational constraints by choosing the right optimization algorithm, including the simplex algorithm.
Abstract:
Real-time drilling optimization is a topic of significant interest because of its economic value, and its importance increases particularly during periods of low oil prices. This paper evaluates different optimization strategies and algorithms for real-time optimization of an objective function (function to be optimized) specific to drilling. The objective function optimized here is derived from a data-driven (or machine-learning) model with an unknown functional form. A data-driven model has been used to calculate the objective function [rate of penetration (ROP)] because it has been shown to be more efficient in ROP prediction relative to deterministic models (Hegde and Gray 2017). The data-driven ROP model is built using machine-learning algorithms; measured drilling parameters [weight on bit (WOB), revolutions per minute (rev/min), strength of rock, and flow rate] are used as inputs to predict the ROP.
Real-time drilling optimization that is data-driven is challenging because of run-time constraints. This is perceived as a handicap for data-driven models because their functional form is unknown, making them more difficult to optimize. This paper evaluates algorithms depending on their ability to best maximize the objective (ROP) and their time effectiveness. Two simple yet robust algorithms, the eyeball method and the random-search method, are presented as plausible solutions to this problem. These methods are then compared with popular metaheuristic algorithms, evaluating the tradeoff between improvement in the objective (search for a global optimal) and the computational time of run.
Using results from the simulations conducted in this paper, we concluded that data-driven models can be used for real-time drilling despite their computational constraints by choosing the right optimization algorithm. The best tradeoff in terms of ROP increase as well as computational efficiency evaluated in this paper is the simplex algorithm. The ROP was improved by 30% on average with a variance of 2.5% in the test set over 14 formations that were tested.
49 citations
References
More filters
01 Jan 1994
53 citations
01 Jan 2012
38 citations
25 citations
01 Jan 2008
TL;DR: In this article, the rate of penetration of a new well in the Persian Gulf carbonate field has been optimized using the ROP models for upcoming wells in a simple and useful simulator.
Abstract: Improving the rate of penetration (ROP) is one of the key methods to reduce drilling costs. Several ROP models have been developed and modified based on the concept where unconfined compressive strength (UCS) is inversionally proportional with the rate of penetration. These models can predict the rate of penetration of different bit types in an oil or gas field with a reasonable degree of accuracy. The ROP model studied herein relates the rate of penetration to operating conditions and bit parameters in addition to the rock strength. Also, the effects of bit hydraulics and bit wear on rate of penetration are included in the model. In this paper, the drilling performance was optimized, using the ROP models, for upcoming wells in one of the Persian Gulf carbonate fields. Based on previous drilled wells a rock strength log along the wellbore is created and modified to mach the the new well survey. The rock strength is back calculated from the ROP model which includes bit design and reported field wear in conjunction with meter by meter operating parameters, formation lithologies and pore pressure. By conducting a number of simulations a learning curve was constructed to obtain the optimum bit hydraulics, best combination of operational parameters and the most effective bit design. Based on the proposed ROP model, a simple and useful simulator was developed. This methodology can be used in pre-planning and post analysis to reduce drilling cost where previously drilled wells exist.
20 citations
01 Jan 2007
TL;DR: In this paper, the use of the dynamic measurements and the application of some drilling models in analyzing formation changes while drilling, and use of these data and models in simulating drilling dynamics.
Abstract: As a result of bit-rock interaction, downhole weight-on-bit, downhole torque, instantaneous downhole rotational speed and bit motion (acceleration and rate of penetration) are directly affected by the formations being drilled. Since these measurements react differently to different lithologies, and assuming that drilling problems do not effect these measurements, any changes in the measurements in some way will reflect changes in the properties of the lithology. If, based on these measurements, the lithology is assumed to have certain properties, then it is possible to derive models for the interaction between bit, formation and drillstring. With these models it is possible to simulate the dynamic behavior of the system including phenomena like stick-slip. Rate of penetration has long been used as a lithology indicator, and drilling models have been developed using surface measured drilling parameters to infer changes in lithology. With the advent of MWD measurements, significant improvements were made in the mathematical models by involving downhole torque. The model derived parameters were shown to be related to rock strength (drilling and shear strength) and proved to be good indicators of formation changes. Similar expressions in the form of simple bit models can be used in combination with a finite element model of the drillstring to simulate the dynamic behavior of the complete system. A significant improvement in this analysis can be affected by introducing measurements from the dynamics tool, such as instantaneous torque, weight and rotation rate, as well as the bit acceleration. These measurements provide not only static but also dynamic data which can be used to validate simulations and the underlying models. The present analysis explores the use of the dynamic measurements and the application of some drilling models in analyzing formation changes while drilling, and the use of these data and models in simulating drilling dynamics.Copyright © 2007 by ASME
17 citations