Drill Bit Failure Forensics Using 2D Bit Images Captured at the Rig Site

Abstract

Identifying the root cause of damage of a pulled bit as soon as possible will aid in preparation for future drilling operations. Today, bit damage analyses are often time-consuming, delayed, subjective, and error prone. A novel automated forensics approach is presented in this paper for polycrystalline diamond compact (PDC) bit damage root cause analysis using 2D bit photos that can be easily captured on a phone or camera at the rigsite. A labeled data set consisting of 125 actual bit images and 800 synthetic images was first created with the cutters appropriately identified and labeled. Using this data set, a convolutional neural network (CNN) along with other image processing techniques was applied to first identify the individual cutters and their positions on the bit and then to quantify the damage to the cutters. A cutter detection accuracy of over 97% and a damage quantification accuracy of 97% were achieved. A separate classifier was then trained to directly identify the root cause of failure from the bit images. This classifier utilized a separate data set that consisted of multiple bit images from 25 distinct bit runs. This data set was labeled into different types of failure mechanisms through analysis by a subject-matter expert. The trained classifier developed could properly identify the root causes of failure when the bit photo quality met certain minimum standards. One key observation was that bit images are not always captured appropriately, and this reduces the accuracy of the proposed methodology. By identifying the potential root causes of PDC damage through image processing, drilling parameters can be optimized to prolong future bit life.