Development of an Adaptive Algorithm for PDC Bit Wear Rate Prediction in Oil and Gas Well Drilling Considering Formation’s Geomechanical Characteristics

Abstract

Bit wear is one of the fundamental challenges affecting the performance cost of drilling operations in oil, gas, and geothermal wells. Since identifying the factors influencing bit wear rate (BWR) is essential, and the ability predict its variations during drilling operations is influenced by environmental and operational factors, this study aims to develop an Adaptive Bit Wear Predictor (ABWRP) algorithm for estimating the BWR during drilling operations for new wells. The structure of this algorithm consists of a transmitter, data processor, deep learning-based bit wear rate estimator, and bit wear updating module. To develop a model for the BWR estimation module, data from two wells in an oil field in southwest Iran were collected and analyzed, including petrophysical data, drilling data, and bit wear and records. Both studied wells were drilled using PDC bits with a diameter of inches. After preprocessing the data, the key factors affecting the bit wear were identified using the Wrapper method, including depth, confined compressive strength, maximum horizontal stress, bit wear percentage, weight on bit, bit rotational speed, and pump flow rate. Subsequently, seven machine learning (ML) and deep learning (DL) algorithms were used to develop the wear rate estimation module within the ABWRP algorithm. Among them, convolutional neural network (CNN) model demonstrated the performance, with Root Mean Square Error (RMSE) values of 0.0011 0.0017 and R-square (R2) values of 0.96 and 0.92 for the training and testing datasets, respectively. Therefore, the CNN model was selected as the most efficient model among the evaluated models. Finally, a simulation-based experiment was designed to evaluate the performance of the ABWRP algorithm. In this experiment, unseen data from one of the studied wells were used as data from a newly drilled well. The results demonstrated that ABWRP algorithm could estimate final bit wear with a 14% error. Thus, algorithm developed in this study can play a significant role in the design planning of new wells, particularly in optimizing drilling parameters while considering bit wear effects.