Improved Water Based Mud Using Solanum Tuberosum Formulated Biopolymer and Application of Artificial Neural Network in Predicting Mud Rheological Properties

Abstract

Drilling fluids are the most important materials in drilling operations, therefore improving the properties of these fluids are very essential in order to meet up with the increase in demands and required standards. In this experimental study, Solanum tuberosum formulated biopolymer was used to improve the water based mud rheological properties and artificial neural network predicted data for (PV) plastic viscosity, (AP) apparent viscosity and (YP) yield point. Artificial neural network (ANN) was used to train the rheological properties of the formulated mud and the network developed predicted the rheological properties of an untrained combination of bentonite and modified biopolymer. The main target is to regenerate or predict the rheological properties of the formulated mud; (AP) apparent viscosity, (YP) yield point and (PV) plastic viscosity generated originally from experimental procedures but this time using the ANN. The mean average error target was set to around 5-10%. As a model for choosing the best ANN architecture for predicting target value, two statistical parameters, mean squared error (MSE) and correlation coefficient (R2) were utilized. A system with the lower estimations of MSE and the higher estimations of R2 gives more precise forecasts. Three different network were created and the two statistical parameters were used to determine the best number of neurons in the hidden layer. The developed neural network with best prediction has Root Mean Square Error (MSE) of 1.25221 and overall correlation coefficient (R2) of 0.99373 for the predicted plastic viscosity, yield point and apparent viscosity

Application of soft computing approaches for modeling annular pressure loss of slim-hole wells in one of Iranian central oil fields

“…ANN is an innovative soft computing (SC) method with specific performance characteristics which are close to the biologic neural structure (Osman and Aggour, 2003;Mohaghegh, 2000;Tomiwa et al, 2019;Specht et al, 2007). An ANN model structurally consists of three different components, i.e.…”

Application of soft computing approaches for modeling annular pressure loss of slim-hole wells in one of Iranian central oil fields

“…ANN is an innovative soft computing (SC) method with specific performance characteristics which are close to the biologic neural structure (Osman and Aggour, 2003;Mohaghegh, 2000;Tomiwa et al, 2019;Specht et al, 2007). An ANN model structurally consists of three different components, i.e.…”

Prediction of the Rheological Properties of Invert Emulsion Mud Using an Artificial Neural Network

“…Huang used regression analysis to develop a predictive mathematical model for estimating poly-sulfonated drilling fluid apparent viscosity. Tomiwa established a single hidden layer with seven neurons ANN model using 65 actual field measurements. His proposed model could estimate the WBM yield point, plastic viscosity, and apparent viscosity based on the bentonite and solanum tuberosum biopolymer quantities within the mud.…”

“…Al-Khdheeawi used 142 actual datasets to develop the ANN model and nonlinear multiple regression correlation that both could estimate WBM apparent viscosity based on marsh funnel viscosity and mud weight. Tomiwa established an ANN model with a single hidden layer that contains 15 neurons; the model could be utilized for estimating apparent viscosity, plastic viscosity, and yield point of modified biopolymer WBM based on 100 actual datasets, water volume, biopolymer, and bentonite concentrations, which were selected as input features. Gowida developed another ANN model for predicting WBM plastic viscosity and apparent viscosity using mud weight and marsh funnel viscosity as input parameters, and 200 actual datasets were employed to develop such a model.…”