Drilling efficiency enhancement in oil and gas domain using machine learning
by Aditi Nautiyal; Amit Kumar Mishra
International Journal of Oil, Gas and Coal Technology (IJOGCT), Vol. 32, No. 4, 2023

Abstract: Oil and gas are non-renewable natural resources that require a great marvel of engineering, planning, and huge capital investment. Drilling efficiency enhancement means increasing the rate of penetration (ROP) and avoiding downhole complications like stuck pipe, wellbore collapse, etc. Drilling is a complex activity, prediction of ROP and downhole complications depend upon the various drilling parameters, bottom hole assembly designing, drill bit selection, mud type, mud weight selection, well trajectory designing, revolutions per minute (RPM), and formation parameters which exhibit linear or nonlinear relationships with the objective function. This research work is focused on machine learning algorithms like random forest, artificial neural network, etc., for the development of the ROP prediction model. Hyperparameter tunning methods like RandomisedSearchCV() were used to enhance model accuracy, the evolutionary particle swarm optimisation (PSO) algorithm to maximise ROP, and an exhaustive list of parameters deemed necessary for the development of an accurate and generalised ML model. [Received: June 28, 2022; Accepted: September 18, 2022]

Online publication date: Tue, 14-Mar-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Oil, Gas and Coal Technology (IJOGCT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com