Modeling and Simulation of Rock Bits Based on Mega Drilling Data

Abstract

Rock bits directly undertake the task of fracturing rock under earth during drilling operation. Accurate prediction of Rate of penetration (ROP) play an important role in reducing drilling costs and shortening the drilling cycle. This paper introduces ROP prediction methods including empirical mathematical modeling, computer simulation of bit-rock interaction and BP neural network model based on mega drilling data. The most significant factors affecting ROP are summarized as follows: weight on bit(WOB), rotation speed, rock formation properties, bit cutting structure, etc., which have a complex multi-parameter nonlinear relationship with ROP. The drilling data features complexity and big volume. Therefore machine learning is a best way to model the relationship between main factors and ROP. The advantages and disadvantages of the different ROP modeling methods are analyzed and compared. It shows that the BP neural network model based on mega drilling data demonstrates high accuracy, and is the future development direction in ROP prediction.