<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Rezki Djamil</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Using a data mining CRISP-DM methodology for rate of penetration (ROP) prediction in oil well drilling</style></title><secondary-title><style face="normal" font="default" size="100%">Proceedings of the International Conference on Industrial Engineering and Operations Management Paris, France</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2018</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://hal-amu.archives-ouvertes.fr/hal-02482291/document</style></url></web-urls></urls><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;span style=&quot;left:120.04px;top:465.223px;18.4px;sans-serif;transform:scaleX(0.895548);&quot;&gt;This work describes an implementation of a oil drilling data mining project approach based on the &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:486.223px;18.4px;sans-serif;transform:scaleX(0.934819);&quot;&gt;CRISP-DM methodology. Recent real-world data were collected from a from historical data of an actual &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:507.423px;18.4px;sans-serif;transform:scaleX(0.951083);&quot;&gt;oil drilling process in Hassi Terfa field, situated in South of Algeria. During the modelling process. The &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:528.423px;18.4px;sans-serif;transform:scaleX(0.893623);&quot;&gt;goal was to predict the rate of penetration (ROP) based on input parameters that are commonly used at the &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:549.423px;18.4px;sans-serif;transform:scaleX(0.926122);&quot;&gt;oil drilling process (weight on bit, rotation per minute, mud density , spp, ucs) . At the data preparation &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:570.624px;18.4px;sans-serif;transform:scaleX(0.914872);&quot;&gt;stage, the data were cleaned and variables were selected and transformed. Next, at the modeling stage, a &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:591.624px;18.4px;sans-serif;transform:scaleX(0.908659);&quot;&gt;regression approach was adopted, where three learning methods were compared : Artificial Neural &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:612.824px;18.4px;sans-serif;transform:scaleX(0.880932);&quot;&gt;Network, Support Vector Machine and Random Forest. The best learning model was obtained by the &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:633.824px;18.4px;sans-serif;transform:scaleX(0.906409);&quot;&gt;Random Forest method, which presents a high quality coefficient of correlation. The results of the &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:654.824px;18.4px;sans-serif;transform:scaleX(0.858435);&quot;&gt;experiment show that the proposed approach is able to effectively use the engineering data to provide &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:676.023px;18.4px;sans-serif;transform:scaleX(0.933827);&quot;&gt;effective prediction ROP, the ROP prediction allows the drilling engineer to select the best combination &lt;/span&gt;&lt;span style=&quot;left:120.04px;top:697.059px;18.4px;sans-serif;transform:scaleX(0.885888);&quot;&gt;of the input parameters to have a better advancement&lt;/span&gt;</style></abstract></record></records></xml>