SPE-206235-MS

Real Time Automation of Cutting Carrying Capacity Index to Predict Hole

Cleaning Efficiency and Thereby Improve Well Drilling Performance

Downloaded from http://onepetro.org/SPEATCE/proceedings-pdf/21ATCE/1-21ATCE/D012S067R001/2489501/spe-206235-ms.pdf by Saudi Aramco user on 27 March 2022

Mohammed M Al-Rubaii, Saudi Aramco D&WO; Dhafer Al-Shehri and Mohamed N Mahmoud, KFUPM; Saleh M
Al-Harbi and Khaled A Al-Qahtani, Saudi Aramco D&WO

Copyright 2021, Society of Petroleum Engineers

This paper was prepared for presentation at the 2021 SPE Annual Technical Conference and Exhibition held in Dubai, UAE, 21 - 23 September 2021.

This paper was selected for presentation by an SPE program committee following review of information contained in an abstract submitted by the author(s). Contents
of the paper have not been reviewed by the Society of Petroleum Engineers and are subject to correction by the author(s). The material does not necessarily reflect
any position of the Society of Petroleum Engineers, its officers, or members. Electronic reproduction, distribution, or storage of any part of this paper without the written
consent of the Society of Petroleum Engineers is prohibited. Permission to reproduce in print is restricted to an abstract of not more than 300 words; illustrations may
not be copied. The abstract must contain conspicuous acknowledgment of SPE copyright.

Abstract
Hole cleaning efficiency is one of the major factors that affects well drilling performance. Rate of penetration
(ROP) is highly dependent on hole cleaning efficiency. Hole cleaning performance can be monitored
in real-time in order to make sure drilled cuttings generated are efficiently transported to surface. The
objective of this paper to present a real time automated model to obtain hole cleaning efficiency and thus
effectively adjust parameters as required to improve drilling performance. The process adopts a modified
real time carrying capacity indicator. There are many hole cleaning models, methodologies, chemicals
and correlations, but majority of these models do not simulate drilling operations sequences and are
not dependent on practicality of drilling operations. The developed real time hole cleaning indicator can
ensure continuous monitoring and evaluation of hole cleaning performance during drilling operations. The
methodology of real time model development is by selecting offset mechanical drilling parameters and
drilling fluid parameters where collected, analyzed, tested and validated to model strong hole cleaning
efficiency indicator that can extremely participate and facilitate a position in drilling automations and fourth
industry revolution. The automated hole cleaning model is utilizing real time sensors of drilling and validate
the strongest relationships among the variables. The study, analysis, test and validation of the relationships
will reveal the significant parameters that will contribute massively for model development procedures.
The model can be run as well by using the real time sensors readings and their inputs to be fed into the
developed automated model. The developed model of real time carrying capacity indicator profile will be
shown as function of depth, drilling fluid density, flow rate of mud pump or mud pump output, and other
important factors will be illustrated by details. The model has been developed and validated in the field of
drilling operations to empower the drilling teams for better and understandable monitoring and evaluation
of hole cleaning efficiency while performing drilling operations. The real time model can provide a vision
for better control of mud additives and that will contribute to mud cost effectiveness.
The automated model of hole cleaning efficiency optimized the rate of penetration (ROP) by 50% in
well drilling performance as a noticeable and valuable improvement. This optimum improvement saved
cost and time of rig and drilling of wells and contributed to accelerate wells’ delivery. The innovative real
time model was developed to optimize drilling and operations efficiency by using the surface rig sensors
and interpret the downhole measurements and that can lead innovatively to other important hole cleaning
2 SPE-206235-MS

indicators and other tactics for better development of downhole measurements models that can participate
for optimized drilling efficiency.

Introduction
The efficient hole cleaning and cutting transport are challenges in planning and drilling vertical, deviated,
high angle and extended reach wells. Cuttings transport optimization depends on several factors such as;
cutting size, optimization of bit hydraulics, hole angle, drill string rotation, drill pipe eccentricity, etc. Up to

Downloaded from http://onepetro.org/SPEATCE/proceedings-pdf/21ATCE/1-21ATCE/D012S067R001/2489501/spe-206235-ms.pdf by Saudi Aramco user on 27 March 2022

date, most hole cleaning models existing and charts have been derived for wells with angles greater than 25
degrees, these models use charts developed from the original physical based model. Hole cleaning has been
evaluated by calculating the carrying capacity in vertical holes, and most hole cleaning charts do not apply to
vertical and near vertical wells. More extended reach wells, ultra-deep and highly deviated wells are being
drilled to meet the continues energy demand. Hole cleaning during drilling is one of the major challenges
in highly deviated and extended reach wells. However poor hole cleaning can cause some drilling problems
including: stuck pipe, possible hole pack-off, excessive ECD, formation fracture and cutting accumulation.
The key to a successful hole cleaning relies upon integrating optimum drilling fluid properties with best
drilling practices.
For optimal hole cleaning during drilling, the removal of drill cutting must be efficient. Many studies
have been conducted to identify some of the factors affecting hole cleaning. The basic medium for cuttings
transport during drilling is via the circulation fluid that is known as the drilling fluid. Cuttings suspension
and transport are one of the most important properties to be considered when selecting the drilling fluid. In
order to efficiently transport cuttings out of the hole, the transporting medium (drilling fluid) must be able
to suspend the solid particles (cuttings). Also, there must be enough energy in the form of motion to push
the solids out of the hole. The factors that affect the ability of the drilling fluid to efficiently transport the
drilling cuttings to the surface and provide optimal hole cleaning are many, and some of these factors are:
cutting density and mud weight, hole size and hole-angle, rheology of circulation fluid, cutting size, hole-
cleaning pills, rate of penetration, drill pipe eccentricity, drill pipe rotation, multi-phase flow effect, cutting
transport ratio and cutting bed properties.
Many studies have been conducted through the years to understand the factors that affect the hole cleaning
efficiency. The formation cutting bed as the hole angles between 35-50 degrees of inclination more likely
to slide downwards (Tomren et al. 1986; Peden et al. 1990; Sifferman and Becker 1992). The cutting beds
height decreases by increasing the pumping flow rate Tomren et al. (1986), Li and Walker (1999) and Hyun
et al. (2001). The mud rheology affects the hole cleaning as the experimental investigations done by Hussaini
and Azar (1983), Okranji and Azar (1986) and Azar (1990) showed that by increasing the ratio between the
yield point (YP) and the plastic viscosity (μp) the carrying capacity of the mud increases. Also, the lower
the viscosity of the mud the better the hole cleaning is and the higher the tendency of the cuttings to roll
(Ford et al., 1990). The pipe rotation greatly improves the hole cleaning when the pipe is eccentric Ravi and
Hemphill (2006), and for inclined hole sections too Sanchez et al. (1999). Ogunrinde and Dosunmu (2012)
developed model to estimate the optimum ROP and GPM used while drilling.
The artificial intelligence tools can also be used to developed intelligent model for prediction of hole
cleaning performance. ANN (Artificial Neural Network) which is inspired from the biological neurons
found in the human brains. ANN is the most powerful statistical tool to classify and recognize complex
patterns and system (Huang 1996 and Castillo 2012). ANFIS (Adaptive Neuro-Fuzzy Inference System) is
the combination of neural network and fuzzy logic. It is a better learning ability with smaller convergence
error that can be achieved. The smallness of error in ANFIS can compensate the slowness of the
convergence. Also, ANFIS need less adjustable parameters than are required in other neural network
structures such as backpropagation MPLs (Walia et al., 2015). SVM (Support Vector Machine) is used
mostly for regression and pattern recognition purposes (Burbidge et al. 2001 and Ben-Hur et al. 2001).
SPE-206235-MS 3

Hyper-plane support vector machine based on soft margin have been introduced as a new artificial
intelligence tool of framework for both function approximation and classification (Jeng et al. 2003 and
William et al. 2007). SVM is founded in many fields such as electrical, medical, etc. (Gholami et al. 2012).
Mohammed M Al-Rubaii et al. (2018) developed a new robust approach for hole cleaning to improve rate
of penetration by monitoring and controlling simultaneously the carrying capacity index and the cuttings
concentration in the annulus to ensure perfect hole cleaning. The drilling performance has been improved
by more than 55%. An automated evaluation model of hole cleaning efficiency while drilling was developed
by Mohammed M Al-Rubaii et al. (2020) to improve the rate of penetration. As a result of the drilling rate

Downloaded from http://onepetro.org/SPEATCE/proceedings-pdf/21ATCE/1-21ATCE/D012S067R001/2489501/spe-206235-ms.pdf by Saudi Aramco user on 27 March 2022

(rate of penetration) has been improved by more than 50%.

Methodology and Validation

In this paper a new real time developed model based on carrying capacity indicator (CCI) considers the
important factors for hole cleaning efficiency. The development of this model started from the CCI model
in Eq. 1, by defining the consistency index (k) with low shear yield point (LSYP) as in Eq. 2. The original
k and n do not contain LSYP. Here in the developed real time model K & n take LSYP in account, LSYP
term contains R3 & R6 which they are viscometer readings device at 3-RPM and at 6-RPM.
Eq. 1

Eq. 2

Where PV denotes the drilling fluid plastic viscosity (cP), YP is the drilling fluid yield point (lb/100ft2),
R3 viscometer reading at 3 RPM and R6 is viscometer reading at 6 RPM for seeking to predict low shear
yield point (LSYP), n is the flow behavior index which we define as a function of the drilling fluid plastic
viscosity, yield point and LSYP as in

Eq. 3

Substituting Eq. 2 and into Eq. 1 and replacing the CCI with the new parameter which we call the hole
cleaning Indicator (HCI) will yield Eq. 4.

Eq. 4

The Annulus velocity (AV) in Eq. 4 is a drilling parameter which can be expressed as a modified annulus
velocity (AVm) that is composed of the corrected annular velocity that can ensure the consideration of
inclination influence on annular velocity and slip velocity of cuttings, the summation of theses velocities is
called transport velocity or modified annular velocity that is required to transport cuttings to surface. (Eq. 5).

Eq. 5

Where Vcorrected and Vslip denote the cutting transport velocity in (ft/min). Vcorrected and Vslip are defined as:

Eq. 6
4 SPE-206235-MS

Eq. 7

Downloaded from http://onepetro.org/SPEATCE/proceedings-pdf/21ATCE/1-21ATCE/D012S067R001/2489501/spe-206235-ms.pdf by Saudi Aramco user on 27 March 2022

Eq. 8

Corrected Velocity is a function of mud pump flow rate (GPM) in gallon per minute, hole size (OH) in
inches, Drill pipe outer diameter in inches, rate of penetration (ROP) in feet per hour (ft/hr), inclination (α)
and azimuthal (β) directions of hole section in degrees (deg). V-corrected mainly is composed of Annular
velocity, cutting rise velocity and critical velocity respectively as shown in Eq.6. while slip velocity includes
annular velocity, mud weight in pound per cubic feet (PCF), ROP and drill string rotation that is revolution
per minute (rev/min), hole size, outer diameter of drill pipe and apparent viscosity which is the large term in
equation that contains consistency and flow behavior indices of drilling fluid rheology. Now, by replacing
the mud weight (MW) in Eq. 4 and by the equivalent mud weight (EMW) in the annulus that contain original
designed drilling fluid weight and cuttings weight that is generated while drilling due to used ROP, and that
could be done by calculating cuttings concentration (CC) in anulus multiplied by designed mud weight that
was prepared to be used in the drilled hole section with original designed mud weight. This methodology
called integration models by combining cutting concentration in annuls with mud weight which finally lead
to equivalent mud density while drilling by substituting for the values in Eq. 59 with Eq.10 of CC to get
EMW, the HCI in Eq.11 parameter could be summarized as:
Eq. 9

Eq. 10

Eq. 11

Where the HCI is a hole cleaning indicator which takes into accounts the effect of most of the influential
parameters which affect the hole cleaning condition, Kn accounts for the effect of the rheological parameters
of the drilling fluid (i.e. the plastic viscosity, yield point and LSYP), EMW accounts for the effects of
the CC with original designed mud weight. The real time HCI includes many inputs such as drilling fluid
rheological parameters, drilling mechanical parameters, well trajectory survey, and mud velocities. For all
the early developed hole cleaning models there were a classification ranges considered to judge on the hole
cleaning conditions, therefore, in this Paper, a classification range for the HCI parameter will be developed,
this classification is basically developed from the CCI classification which has two ranges of CCI > 1 where
the hole cleaning is good, and CCI ≤ 1 for bad hole cleaning condition. The CCI classification was extended
for the developed HCI model to be as follow:

• HCI > 1 for good hole cleaning conditions.

• HCI ≤ 1 represents the insufficient hole cleaning situation that might lead drilling hole problems.
In this case immediate action should be taken, drilling must be stopped, and hole must be circulated
while working pipe up and down.
SPE-206235-MS 5

Results and Discussion

By applying the developed model on real time values, the real time profile of developed model of HCI
is generated. After applying the developed model on real time offset well (blue real time profile) values,
the HCI showed low values less than 1, hence we can conclude that the well drilling performance was not
optimum. However, once the developed model of HCI deployed on a trial well (orange real time profile)
real time values of well in field, the real time values of HCI was more than 1 which means that, ROP
is optimized and well drilling performance can be improved. After applying HCI on offset well, that the

Downloaded from http://onepetro.org/SPEATCE/proceedings-pdf/21ATCE/1-21ATCE/D012S067R001/2489501/spe-206235-ms.pdf by Saudi Aramco user on 27 March 2022

HCI was not followed, the drilling team was not aware about that they need to have better hole cleaning
efficiency to enhance ROP. On the other hand, once the drilling team applied the HCI on real time on the
trial well to validate and follow the real time developed model of HCI, the HCI showed real time values
more than 1, which means that the drilling team relized that ROP can be enhanced because they have better
HCI. Better HCI means effective hole cleaning performance. The real time values of HCI for offset and
trial wells indicate that if HCI is more than 1, ROP can be more or optimized and vise versa. The trial wells
showed high ROP since HCI was high and that means with more hole cleaning efficiency, more proper
optimized ROP can be obtained. The application of HCI can ensure ROP improvement by 50 % as can be
seen in figure-1.

Figure 1—ROP improvement and HCI evaluation for offset and trial wells.

Conclusion and Recommendations

The developed and automated models can be used to evaluate the hole cleaning performance in the wellbore
from other operational parameters. The new model has a great impact on the effectiveness of hole cleaning.
Data analytics process such as (data preparation, data preprocessing, data transformation and data mining
and data evaluation) were applied to come up with strong model that can be trustable and strong. The
6 SPE-206235-MS

developed automated model using unseen real time values from the same field has been validated. The
well drilling performance improved by 50%. It is highly recommended to apply the automated model to
ensure constant values such as real time evaluation for hole cleaning efficiency, optimized well drilling and
operations performance and finally minimize hole Problems.

References
Azar, J.J. (1990). Does Mud Rheology Play a Major Role in Hole Cleaning of Highly deviated Wells? Latin American
Drilling Conference, Venezuela.

Downloaded from http://onepetro.org/SPEATCE/proceedings-pdf/21ATCE/1-21ATCE/D012S067R001/2489501/spe-206235-ms.pdf by Saudi Aramco user on 27 March 2022

Ben-Hur A H, S H David, and V. Vapnik (2001). Support vector clustering. Journal of Machine Learning Research, v.
2: pp.125–137.
Burbidge R, M. Trotter, and B. Buxto (2001). Drug design by machine learning: support vector machines for
pharmaceutical data analysis. Comput Chem,, 26 (1):5–14
Castillo, A.Á.D., E. Santoyo, O. Garcia-Valladare (2012). A new void fraction correlation inferred from artificial neural
networks for modeling two-phase flows in geothermal wells. Comput. Geosci. 41, 25–39.
Gholami R Shahraki A R, Jamali P M. Prediction of hydrocarbon reservoirs permeability using support vector machine.
Mathematical Problems in Engineering, 2012, doi: 10.1155/2012/670723.
Huang, Z., Shimeld, J., Williamson, M. 1996. Permeability prediction with artificial neural network modeling in the
Venture gas field, offshore eastern Canada. Geophysics 61(2):422–436
Hussaini, S. M., & Azar, J. J. (1983). Experimental Study of Drilled Cuttings Transport Using Common Drilling Muds.
Society of Petroleum Engineers Journal, 23(01), 11-20. doi: 10.2118/10674-PA
Hyun, C., Shah, S., & Osisanya, S. (2001). Effects of Fluid Flow in a Porous Cuttings-Bed on Cuttings Transport Efficiency
and Hydraulics. Proceedings of SPE Annual Technical Conference and Exhibition. doi: 10.2523/71374-MS
Jeng J T, Chuang C C, Su S F. Support vector interval regression networks for interval regression analysis. Fuzzy Sets
Syst, 2003, 138 (2):283–300.
Li, J., & Walker, S. (1999). Sensitivity Analysis of Hole Cleaning Parameters in Directional Wells. Society of Petroleum
Engineers. doi: 10.2118/54498-MS
Ogunrinde, J. O., & Dosunmu, A. (2012, January 1). Hydraulics Optimization for Efficient Hole Cleaning in Deviated
and Horizontal Wells. Society of Petroleum Engineers. doi: 10.2118/162970-MS
Okrajni, S., & Azar, J. J. (1986, August 1). The Effects of Mud Rheology on Annular Hole Cleaning in Directional Wells.
Society of Petroleum Engineers. doi: 10.2118/14178-PA.
Peden, J., Ford, J., & Oyeneyin, M. (1990). Comprehensive Experimental Investigation of Drilled Cuttings Transport
in Inclined Wells Including the Effects of Rotation and Eccentricity. European Petroleum Conference. doi:
10.2118/20925-MS.
Ravi, K., & Hemphill, T. (2006). Pipe Rotation and Hole Cleaning in Eccentric Annulus. Proceedings of IADC/SPE
Drilling Conference. doi: 10.2523/99150-MS
Ravi, K., & Hemphill, T. (2006, January 1). Pipe Rotation and Hole Cleaning in Eccentric Annulus. Society of Petroleum
Engineers. doi: 10.2118/99150-MS.
Sanchez, R. A., Azar, J. J., Bassal, A. A., & Martins, A. L. (1999, June 1). Effect of Drillpipe Rotation on Hole Cleaning
During Directional-Well Drilling. Society of Petroleum Engineers. doi: 10.2118/56406-PA
Sifferman, T., & Becker, T. (1992). Hole Cleaning in Full-Scale Inclined Wellbores. SPE Drilling Engineering, 7(02),
115-120. doi: 10.2118/20422-PA
Tomren, P., Iyoho, A., & Azar, J. (1986). Experimental Study of Cuttings Transport in Directional Wells. SPE Drilling
Engineering, 1(01), 43-56. doi: 10.2118/12123-pa
Walia, N., Singh, H., Sharma, A., 2015. ANFIS: Adaptive Neuro-Fuzzy Inference System-A Survey. Int. J. Comput. Appl.
123, 32–38. doi:10.5120/ijca2015905635
William H, Teukolsky S A, Vetterling W T, Flannery B P. Support Vector Machines. Numerical Recipes: The Art of
Scientific Computing (3rd ed.). New York: Cambridge University Press. 2007, ISBN 978-0-521-88068-8.
Al Rubaii, Mohammed Murif. "A New Robust Approach for Hole Cleaning to Improve Rate of Penetration." Paper
presented at the SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition, Dammam, Saudi Arabia,
April 2018. doi: https://doi.org/10.2118/192223-MS
Al-Rubaii, Mohammed Murif, Gajbhiye, Rahul N., Al-Yami, Abdullah, Alshalan, Meshari, and Mohammed B. Al-Awami.
"Automated Evaluation of Hole Cleaning Efficiency While Drilling Improves Rate of Penetration." Paper presented at
the International Petroleum Technology Conference, Dhahran, Kingdom of Saudi Arabia, January 2020. doi: https://
doi.org/10.2523/IPTC-19809-MS