International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 22 (2017) pp. 12880-12891
© Research India Publications. http://www.ripublication.com
12880
Modeling of Drilling Rate of Penetration Using Adaptive Neuro-Fuzzy
Inference System
Mohammed Ayoub
1*
, Goh Shien
1
, Diab Diab
1*
and Quosay Ahmed
2
1
Petroleum Engineering Department, Universiti Teknologi, Petronas Bandar Seri Iskandar, 32160 Perak, Malaysia.
2
Department of Oil & Natural Gas Engineering, University of Khartoum, 11111 Khartoum, Sudan.
(*Correspondence Author)
1
Orcid: 0000-0002-5007-779X
Abstract
Drilling rate of penetration (ROP) is a crucial factor in
optimizing drilling cost. This is mainly due to the excessive
cost of the drilling equipment and rig rental, where the longer
the drilling activity would reflect a higher expenditure. If the
drilling rate of penetration can be predicted accurately, we
would be able to avoid unnecessary spending. Hence, this can
lead to minimizing the drilling cost significantly. In this paper,
an Adaptive Neuro-Fuzzy Inference System (ANFIS) model is
generated using MATLAB environment. A total number of 504
data sets from a Sudanese oilfield is used to develop a well-
trained and tested ANFIS model for ROP prediction. The
parameters included in the model generation are: depth, bit size,
mud weight, rotary speed and weight on bit. Training options
were set to give the best predicted ROP against the real data.
This model is proven to give a high performance with an error
as low as 1.47% and correlation coefficient of 98%. With this
model, the estimation of the duration of drilling activities in the
nearby wells can be done accurately if relevant data from the
same reservoir is available. Caution must be taken to avoid
using the results from this model beyond the range of training
data.
Keywords: rate of penetration; neuro-fuzzy; bit size; mud
weight; rotary speed; weight on bit.
INTRODUCTION
Drilling optimization is the key aspect to achieve minimum cost
and making the drilling operation economically feasible. By
understanding the drilling parameters that affect drilling rate of
penetration (ROP), a model can be constructed to predict the
drilling rate of penetration through a formation. The ability to
predict ROP accurately will result in avoiding unnecessary
spending and hence cut the drilling budget considerably. For
this reason, several authors and researchers attempted to
develop a model for ROP prediction. Generally, the drilling rate
of penetration is a dependent parameter that can be predicted as
a function of independent drilling parameters [1]. The drilling
parameters are divided into three categories: formation related,
drilling bit related and hydraulics down hole. There are some
models proposed in the past in the effort of predicting ROP
including Bingham model, Bourgoyne and Young model,
Warren model etc. although these models are less accurate in
predicting ROP, they are always used as a guideline for
modification of mathematical models in these days. In This
paper, a Neuro-Fuzzy model is generated using ANFIS
architecture in MATLAB. A set of data consists of 504 Data
samples from Sudanese oil field was used to train and test the
model. Then, trend analysis is curried out for the Neuro-Fuzzy,
Bingham mode and Bourgoyne and Young model (BYM).
From the results, the Neuro-Fuzzy model shows a high
performance in predicting ROP against the real data. The model
can be used to predict the ROP of the nearby well in the same
reservoir. However, one limitation of Neuro-Fuzzy technique
is that it doesn’t generate a universal model that can be used to
predict ROP for all the fields all over the world. Instead, the
model must be retrained if it is to be used in another reservoir.
It’s also recommended to train the model using a wide range of
data to enhance the model reliability.
FACTORS AFFECTING THE DRILLING RATE OF
PENETRATION (ROP)
Prediction of ROP is a complicated task because it involves
many factors [2, 3]. Researchers realized that ROP is a function
of rock properties such as: the uniaxial compressive and tensile