25-08-2017, 09:32 PM
Abstract
Cutting analysis is a important and crucial task task to detect
and prevent problems during the petroleum well drilling
process. Several studies have been developed for drilling
inspection, but none of them takes care about analysing the
generated cutting at the vibrating shale shakers. Here we
proposed a system to analyse the cutting’s concentration at
the vibrating shale shakers, which can indicate problems
during the petroleum well drilling process, such that the
collapse of the well borehole walls. Cutting’s images are
acquired and sent to the data analysis module, which has
as the main goal to extract features and to classify frames
according to one of three previously classes of cutting’s
volume. A collection of supervised classifiers were applied
in order to allow comparisons about their accuracy and
efficiency. We used the Optimum-Path Forest (OPF), Artificial
Neural Network using Multilayer Perceptrons (ANNMLP),
Support Vector Machines (SVM) and a Bayesian
Classifier (BC) for this task. The first one outperformed all
the remaining classifiers. Recall that we are also the first to
introduce the OPF classifier in this field of knowledge. Very
good results show the robustness of the proposed system,
which can be also integrated with other commonly system
(Mud-Logging) in order to improve the last one’s efficiency.
Index Terms
Cutting analysis, petroleum well drilling monitoring,
optimum-path forest
1. Introduction
Offshore petroleum well drilling is an expensive, complex
and time-consuming operation and it demands a high
qualification level from the drilling executors. One of the
trends of the oil industry is the application of real time
measurements and optimization of production operations
with the purpose of guaranteeing a safe and effective/low
cost drilling execution. Nowadays, there exists several data
acquisition systems for petroleum well drilling monitoring,
in which a large amount of data is generated at each
time. One of these systems is the Mud-logging, which is
responsible for measuring a set of mechanical and geological
parameters. The data generated by Mud-Logging, together
with the cutting analysis produced during the drilling operation,
allows the drilled soil lithological analysis [25], which
are carried out in deep ranges defined by geology. The
generated cutting samples available at the vibrating shale
shakers are examined by some expert technician in order to
evaluate whether a problem is occuring during the drilling
process. Generally, these cuttings have similar shape and
sizes in typical situations, and distortions beyond the known
normal patterns can indicate the presence of some anomaly,
such that the collapse of the well borehole walls.
Some works have been dedicated for monitoring the
petroleum well drilling process [8], [12], [18], [23], but
none of them were guided by the cutting image analysis.
Frantiek et al. [8] proposed to monitor the rock disintegration
process at drilling with the application of accoustic signal.
A Fourier Transform of the generated signal was performed
for further statistical analysis. Serapi˜ao et al. [23] used
artificial immune systems for classification of several stages
in petroleum drilling. Also, the use of artificial intelligence
techniques in petroleum well drilling engineering is not new.
Coelho et al. [3], Fonseca et al. [9] and Yilmaz et al. [27]
used neural networks for monitoring drilling activities, and
Fonseca et al. [10] applied Support Vector Machines for
classification of petroleum well drilling operations.
Cutting analysis is a important and crucial task task to detect
and prevent problems during the petroleum well drilling
process. Several studies have been developed for drilling
inspection, but none of them takes care about analysing the
generated cutting at the vibrating shale shakers. Here we
proposed a system to analyse the cutting’s concentration at
the vibrating shale shakers, which can indicate problems
during the petroleum well drilling process, such that the
collapse of the well borehole walls. Cutting’s images are
acquired and sent to the data analysis module, which has
as the main goal to extract features and to classify frames
according to one of three previously classes of cutting’s
volume. A collection of supervised classifiers were applied
in order to allow comparisons about their accuracy and
efficiency. We used the Optimum-Path Forest (OPF), Artificial
Neural Network using Multilayer Perceptrons (ANNMLP),
Support Vector Machines (SVM) and a Bayesian
Classifier (BC) for this task. The first one outperformed all
the remaining classifiers. Recall that we are also the first to
introduce the OPF classifier in this field of knowledge. Very
good results show the robustness of the proposed system,
which can be also integrated with other commonly system
(Mud-Logging) in order to improve the last one’s efficiency.
Index Terms
Cutting analysis, petroleum well drilling monitoring,
optimum-path forest
1. Introduction
Offshore petroleum well drilling is an expensive, complex
and time-consuming operation and it demands a high
qualification level from the drilling executors. One of the
trends of the oil industry is the application of real time
measurements and optimization of production operations
with the purpose of guaranteeing a safe and effective/low
cost drilling execution. Nowadays, there exists several data
acquisition systems for petroleum well drilling monitoring,
in which a large amount of data is generated at each
time. One of these systems is the Mud-logging, which is
responsible for measuring a set of mechanical and geological
parameters. The data generated by Mud-Logging, together
with the cutting analysis produced during the drilling operation,
allows the drilled soil lithological analysis [25], which
are carried out in deep ranges defined by geology. The
generated cutting samples available at the vibrating shale
shakers are examined by some expert technician in order to
evaluate whether a problem is occuring during the drilling
process. Generally, these cuttings have similar shape and
sizes in typical situations, and distortions beyond the known
normal patterns can indicate the presence of some anomaly,
such that the collapse of the well borehole walls.
Some works have been dedicated for monitoring the
petroleum well drilling process [8], [12], [18], [23], but
none of them were guided by the cutting image analysis.
Frantiek et al. [8] proposed to monitor the rock disintegration
process at drilling with the application of accoustic signal.
A Fourier Transform of the generated signal was performed
for further statistical analysis. Serapi˜ao et al. [23] used
artificial immune systems for classification of several stages
in petroleum drilling. Also, the use of artificial intelligence
techniques in petroleum well drilling engineering is not new.
Coelho et al. [3], Fonseca et al. [9] and Yilmaz et al. [27]
used neural networks for monitoring drilling activities, and
Fonseca et al. [10] applied Support Vector Machines for
classification of petroleum well drilling operations.