Toward reliable model for prediction Drilling Fluid Density at wellbore conditions: A LSSVM model

详细信息    查看全文

• 作者：Mohammad Ali Ahmadi ^{ahmadi6776@yahoo.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Least Square Support Vector Machine (LSSVM) ; Artificial intelligence ; Genetic algorithm ; Drilling fluid density
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：26 October 2016
• 年：2016
• 卷：211
• 期：Complete
• 页码：143-149
• 全文大小：1452 K

文摘

To prevent drilling fluid losses into formation at the High Pressure High Temperature (HPHT) conditions in oil/gas wellbores, it is highly necessary to have enough information about rheology of the drilling fluid. The lack of global model to estimate the density of the drilling fluid at the wellbore conditions has adversely affected the plans of drilling fluid loss control. By gaining from a special sort of soft computing techniques, a new kind of intelligent based model developed by Suykens et al. and based on extended datasets reported in open literatures, it has noticeably become possible to defeat the aforementioned obstacles and elevate the performance of estimating the Drilling Fluid Density (g/cm³). In this regard, least square support vector machine was employed to predict rheology of the drilling fluid at wellbore conditions for different types of drilling fluids including oil based muds, water based muds, gas-aphrons. According to the average absolute relative deviation, correlation coefficient and mean square error (MSE), the proposed low parameter model has an acceptable robustness; integrity and reliability. Therefore, the proposed artificial intelligence based method can be considered as an alternative model to determine the Drilling Fluid Density (g/cm³) at wellbore condition when the essential experimental data are not obtainable or measureable.