Application of Optimized Least Square Support Vector Machine and Genetic Programming for Accurate Estimation of Drilling Rate of Penetration

Application of Optimized Least Square Support Vector Machine and Genetic Programming for Accurate Estimation of Drilling Rate of Penetration

Meysam Naderi (Amirkabir University of Technology, Tehran, Iran) and Ehsan Khamehchi (Amirkabir University of Technology, Tehran, Iran)
Copyright: © 2018 |Pages: 17
DOI: 10.4018/IJEOE.2018100105


This article describes how the accurate estimation of the rate of penetration (ROP) is essential to minimize drilling costs. There are various factors influencing ROP such as formation rock, drilling fluid properties, wellbore geometry, type of bit, hydraulics, weight on bit, flow rate and bit rotation speed. This paper presents two novel methods based on least square support vector machine (LSSVM) and genetic programming (GP). Models are a function of depth, weight on bit, rotation speed, stand pipe pressure, flow rate, mud weight, bit rotational hours, plastic viscosity, yield point, 10 second gel strength, 10 minute gel strength, and fluid loss. Results show that LSSVM estimates 92% of field data with average absolute relative error of less than 6%. In addition, sensitivity analysis showed that factors of depth, weight on bit, stand pipe pressure, flow rate and bit rotation speed account for 93% of total variation of ROP. Finally, results indicate that LSSVM is superior over GP in terms of average relative error, average absolute relative error, root mean square error, and the coefficient of determination.
Article Preview

1. Introduction

In the petroleum industry, drilling rate of penetration (ROP) is a very important factor which strictly determines the drilling costs. In order to minimize drilling costs, it is required to maximize the rate of penetration. Prediction of ROP is a complicating task because of simultaneous impact of various factors on ROP. Rock strength, depth, rheological properties of mud, bottom hole pressure differential (overbalance or under balance), weight on bit, rotational speed of bottom hole assembly, fluid loss characteristics, wellbore diameter, bit type and hydraulics, and cutting transport efficiency are typical factors which control the penetration rate. As drilling expenditure is highly dependent on the ROP, therefore, reliable and accurate estimation of the ROP is of great importance to perform real time optimization during drilling, and also during well planning.

A literature review shows that several methods have been used for prediction of ROP including analytical models (Maurer, 1962; Galle and Woods, 1963; Motahhari et al., 2009), multiple regression analysis and numerical correlations (Bourgoyne and Young, 1973; Bourgoyne and Young, 1974; Tanseu, 1975; Al-Betairi et al., 1988;Fear, 1999), computer based programs (Mechem and Fullerton, 1965; Maidla and Ohara, 1991; Shirkavand et al., 2010; Hankins et al., 2014, Shishavan et al., 2015), stochastic methods (Ritto et al., 2010), semi analytical models (Alum and Egbon, 2011), evolutionary algorithms (Ping et al., 2014), response surface methodology (Keshavarz Moraveji and Naderi, 2016), and artificial neural network (Wang and Salehi, 2015, Elkatatny et al., 2017, Asadi et al., 2017; Eskandarian et al., 2017), machine learning methods (Hegde and Gray, 2017; Hegde et al., 2017).

Complete Article List

Search this Journal:
Open Access Articles
Volume 10: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 9: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing