THE 3
rd
INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
70
Machine learning is one of the newest approaches for accurate estimations
and it gives a minimum value of human-related error [Asad, 2021, 1].
Rate of penetrations indicates a drilling rate
which is a key factor for
better drilling operations. A greater value of penetration rate leads to faster
drilling which in turn contributes to the overall drilling performance. For years,
many deterministic correlations have been used in the industry for
penetration rate predictions. These models
are based on laboratory
experiments or poor correlation between real drilling data. The technological
advancements in computational science and machine learning allow us to
model new data-driven prediction models. These models use different
algorithms to estimate a rate of penetration [Chiranth, 2018, 2].
This paper is written with the purpose of the development of a machine
learning model generated from a drilling data set. For this, data is classified
into two categories: train and test data. The train data is used to generate a
model, while the test data helps to increase the accuracy of the model.
Several algorithms will be used for the machine learning architectures and
their results will be visualised in order to realize the performance accuracy of
each approach.
References
[1] Asad M. E., "Application of Machine Learning Techniques
for Real Time Rate of
Penetration Optimization,"
Abu Dhabi, 2021
[2] Chiranth H., "Rate of Penetration (ROP) Modelling Using Hybrid Models: Deterministic
and Machine Learning", Houston, 2018.
Dostları ilə paylaş: