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

You can access this article if you purchase or spend a download.