The application of predictive analytics to drilling has a strong interest in the industry today. However, without data modeling, drilling operations are subject to unachieved efficiency. It is missing in the literature how to accurately predict the rate of penetration (ROP) when using surface-only measurements. The traditional approach is to estimate ROP from either data measured on the surface or data collected from downhole. Using the first set of data will result in imprecise results and using purely downhole data can be limited by the fact that there is a time lag due to the slow telemetry systems. In this paper, we propose a novel solution utilizing both data sets.
First, to use both downhole and surface parameters, data is normalized and standardized. Then, Random Forest (RF) regression model is introduced to predict downhole data without any time lag. Then, predicted downhole data such as torque and weight on bit are combined with other drilling parameters to build RF and multi-layer perceptron (MLP) regression models.
It was observed that the computed results better fit the field parameters as a result of incorporating the two sets of data. With the availability of surface data and downhole data, applying this technique is not only useful and accurate, but also simple and fast without incurring further cost to the operating company.
Number of Pages
Amer, M. M.,Dahab, A. S., & El-Sayed, A.-A. H. (2017, June 1). An ROP Predictive Model in Nile Delta Area Using Artificial Neural Networks. Society of Petroleum Engineers. doi:10.2118/187969-MS
Bilgesu, H. I.,Tetrick, L. T.,Altmis, U.,Mohaghegh, S., & Ameri, S. (1997, January 1). A New Approach for the Prediction of Rate of Penetration (ROP) Values. Society of Petroleum Engineers. doi:10.2118/39231-MS
Nasir, E., & Rickabaugh, C. (2018, August 28). Optimizing Drilling Parameters Using a Random Forests ROP Model in the Permian Basin. Society of Petroleum Engineers. doi:10.2118/191796-MS
Mantha, B., & Samuel, R. (2016, September 26). ROP Optimization Using Artificial Intelligence Techniques with Statistical Regression Coupling. Society of Petroleum Engineers. doi:10.2118/181382-MS
Bourgoyne, A.T.,Millheim, K.K.,Chenevert, M.E. and Young, F.S.: Applied Drilling Engineering, ninth edition, SPE, Richardson, TX (2003), Vol. 2, p. 232.)
Looking for more?
Some of the OnePetro partner societies have developed subject- specific wikis that may help.