Formation Pressure Abnormality Identification Using Artificial Neural Networks: A Classification Model

Abnormal formation pressure detection is important in drilling operations from technical and economical points of view. Moreover, the abnormality type determination while drilling helps in taking earlier decisions that may save costs and eliminate near miss problems. The available correlations for pore pressure prediction depend on well logging, formation properties, and combination of logging and drilling parameters. These data are not available for all wells in all sections. The objective of this paper is to use artificial neural networks (ANNs) to develop a classification model to classify the abnormality zones in real-time into subnormal or supernormal zones using both mechanical and hydraulic drilling parameters data. The used parameters included rate of penetration (ROP), mud flow rate (Q), standpipe pressure (SPP), weight on bit (WOB), torque (T) and rotary speed (RS). A dataset of around 2, 900 data points were utilized to provide the classification model. The model classifies the pressure abnormality with high accuracy as the percentage of right classifications was around 98.9% for testing dataset and the area under the curve of receiver operating characteristic (ROC) approached 1.