Improved Water Based Mud Using Solanum Tuberosum Formulated Biopolymer and Application of Artificial Neural Network in Predicting Mud Rheological Properties
- Oguntade Tomiwa (Department of Petroleum Engineering, Covenant University) | Rotimi Oluwatosin (Department of Petroleum Engineering, Covenant University) | Ojo Temiloluwa (Department of Petroleum Engineering, Covenant University) | Olabode Oluwasanmi (Department of Petroleum Engineering, Covenant University) | Idaka Joy (Department of Petroleum Engineering, Covenant University)
- Document ID
- Society of Petroleum Engineers
- SPE Nigeria Annual International Conference and Exhibition, 5-7 August, Lagos, Nigeria
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Petroleum Engineers
- 6 in the last 30 days
- 69 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 9.50|
|SPE Non-Member Price:||USD 28.00|
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
|File Size||1 MB||Number of Pages||14|
Barton, D.L., Sviokla, J., 1988. Putting Expert Systems to Work. Havard Business Review. https://hbr.org/1988/03/putting-expert-systems-to-work, Accessed date: 7 June 2017.
Bravo, C., Saputelli, L., Rivas, F., Pérez, A.G., Nikolaou, M., Zangl, G., de Guzman, Neil, Mohaghegh, S., Nunez, G., 2012. State of the art of artificial intelligence and predictive analytics in the E&P industry: a technology survey. In: Paper SPE 150314 Presented at the SPE Western Regional Meeting Held in Bakersfield, California, USA.
Seteyeobot, I., Uma, J. A., & Enaworu, E. (2017). Experimental Study of the Possible use of Locally Derived Plantain Peelings and Rice Husk as Additives for Oil Based Mud at High Temperature - High Pressure Conditions. Paper presented at the SPE Nigeria Annual International Conference and Exhibition, Lagos, Nigeria.