A New Model of ROP Prediction for Drilling Engineering with Data Mining Technology

Abstract

In drilling engineering, predicting the rate of penetration (ROP) is a prominent factor affecting economic and engineering decisions during well planning, which is particularly important for deep wells and ultra-deep wells. Different methods can be utilized in the optimization of drilling. However, traditional methods were always proposed with the use of empirical correlations and simply predictive algorithms, which lacked convenience and accuracy. To improve ROP predicting capabilities, this paper proposes one predicting method called the combined model of AHP (Analytic Hierarchy Process) and BPNN (Back Propagation Neuron Network) based on data mining. The model was built using UCS (Uniaxial Compressive Strength), bit size, bit type, drillability coefficient, gross hours drilled, WOB (Weight on Bit), RPM (Revolutions Per Minute), drilling mud density and AV (Apparent Viscosity) as the input parameters, and obtained the weights of these factors using AHP, then used Neural Network to predict drilling rate. This model improves the rate of convergence and the reliability of results. The validity of this method has been demonstrated with data from an existing field in north-west China. Furthermore, the model can be used in post-well analysis to identify areas where potential drilling performance was not achieved, and help in identifying improvements for future projects.