It is useful during drilling operations to know when bit failure has occurred because this knowledge can be used to improve drilling performance and provides guidance on when to pull out of hole. This paper presents a simple polycrystalline diamond compact (PDC) bit wear indicator and an associated methodology to help quantify wear and failure using real-time surface sensor data and PDC dull images. The wear indicator is used to identify the point of failure, after which corresponding surface data and dull images can be used to infer the cause of failure. It links rotary speed (RPM) with rate of penetration (ROP) and weight-on-bit (WOB). The term incorporating RPM and ROP represents a "sliding distance", i.e. the number of revolutions required to drill a unit distance of formation, while the WOB represents the formation hardness or contact pressure applied by the formation. This PDC bit wear metric was applied and validated on a data set comprised of 51 lateral production hole bit runs on 9 wells. Surface electric drilling recorder (EDR) data alongside bit dull photos were used to interpret the relationship between the wear metric and observed PDC wear. All runs were in the same extremely hard (estimated 35 – 50 kpsi unconfined compressive strength) and abrasive shale formation. Sliding drilling time and off-bottom time were filtered from the data, and the median wear metric value for each stand was calculated versus measured hole depth while in rotary mode. The initial point in time when the bit fails was found to be most often a singular event, after which ROP never recovered. Once damaged, subsequent catastrophic bit failure generally occurred within drilling 1-2 stands. The rapid bit failure observed was attributed to the increased thermal loads seen at the wear flat of the PDC cutter, which accelerate diamond degradation. The wear metric more accurately identifies the point in time (stand being drilled) of failure than the ROP value by itself. Review of post-run PDC photos show that the final recorded wear metric value can be related to the observed severity of the PDC damage. This information was used to determine a pull criterion to reduce pulling bits that are damaged beyond repair (DBR) and reduce time spent beyond the effective end of life. Pulling bits before DBR status is reached and replacing them increases overall drilling performance. The presented wear metric is simple and cost-effective to implement, which is important to lower-cost land wells, and requires only real-time surface sensor data. It enables a targeted approach to analyzing PDC bit wear, optimizing drilling performance and establishing effective bit pull criteria.

IADC dull bit grading is the current industry standard to assess the condition of a drill bit when it comes out of the hole. It is intended to capture the impact of drilling issues (e.g. drilling abrasive hard rock, drilling dysfunctions) on the bit and to improve future bit selection. However, the grading process is manual and subjective, making the bit grading outcome an inconsistent and unreliable metric. Recent advances in image processing and deep learning allow for bit grading to become more consistent and automated. Such a process is described in this paper. The dataset used in this project consisted of multiple images (taken from different perspectives in a random manner) of used drill bits from 13 bit runs across multiple wells. As a preliminary step in developing the approach, only PDC bits were considered in this project. The first task was to identify all the cutters on a drill bit image using Convolutional Neural Networks (CNN). The CNN approach was chosen since it has shown remarkable success in solving the problem of object detection and classification in other fields. Next, the amount of damage to each cutter was quantified using image processing techniques. Finally, from information gathered in the previous steps, a holistic damage assessment of the drill bit was made. The trained CNN was able to detect the cutters in an image to a high degree of accuracy. The accuracy of cutter detection was further improved through the use of heuristics that predict potential locations of cutters based on blade location and shape. The identification of unique cutters from a group of images of the same bit proved more challenging. Since the images could not be appropriately stitched together, each image was graded independently, and a holistic assessment of the bit was made by aggregation of the individual assessments. Additionally, not all of the cutters identified could be positively identified as damaged or not. For example, if the perspective that was available was at a right angle to the cutter's face, it is inherently not possible to quantify the damage. The computer-generated assessment of the bit was validated with collaborative assessments made by multiple human operators. This paper presents a novel approach to bit damage classification that removes the subjective bias that comes with human evaluations. The application of deep learning techniques to cutter identification, damage detection and quantification is unique and has the potential to significantly improve bit design, selection, and thus, drilling efficiency.

This paper establishes drilling surveillance interpretation and monitoring techniques for digital drilling data which can be used to support drilling forensics and improve drilling performance. One significant advancement in the last 20 years has been the widespread availability and use of sensors to monitor all aspects of the drilling process. The majority of sensors will take surface and downhole data at several hundred samples per second, process the data and store a record at one sample per second. The data from these sensors are collated and processed using some form of Electronic Data Recording system. The information is subsequently displayed in realtime and stored for offsite transmittal. This paper extensively evaluates the impact on drilling performance due to how data from such sensors are collected, processed and the information displayed. A number of observations are investigated, analyzed and explained identifying how data quality, consistency, frequency, sensor errors and data artefacts can skew the displayed results. This can critically impact the drilling forensic analysis and subsequent interpretation. Failing to account for these data quality issues in realtime may mask drilling dysfunction causing accelerated damage to the drill bit and drilling assembly. This paper also aims to highlight techniques for displaying and interpreting drilling data to enhance drilling performance as well as diagnose dysfunction during reviews of historic wells. Understanding these limitations in advance and incorporating them in a team's surveillance strategy can help with the diagnosis of drilling dysfunction and aid performance improvement. These recommended practices have been developed to offer a foundation for drilling surveillance, interpretation and monitoring as well as training for the industry. They have been created such that they can grow organically and may be used for developing subsequent industry publications. The work described in this paper is part of a joint International Association of Drilling Contactors (IADC) / Society of Petroleum Engineers (SPE) industry effort to revise the IADC dull grade process.

Identifying the root cause of damage of a pulled bit as soon as possible will aid preparation for future bit runs. Today, such bit damage analyses are often anecdotal, subjective and error-prone. The objective of this project was to develop a software algorithm to automatically analyze 2D bit images taken at the rig site, and to quickly identify the root cause of bit damage and failure. A labelled dataset was first created whereby the damage seen in bit photos was associated with the appropriate root cause of failure. Particular attention was given to the radial position of the cutters that were damaged. Using the 2D bit images (which can be obtained at the rig site), a convolutional neural network along with other image processing techniques were used to identify the individual cutters, their position on the bit, the degree of wear on each cutter. A classifier was then built to directly identify root cause of failure from these images. This work utilized a large dataset of wells which included multiple bit images, surface sensor data, downhole vibration data, and offset well rock strength information. This dataset helped relate the type of dysfunction as seen in the downhole and surface sensor data to the damage seen on the bit. This dataset however only covered some types of dysfunctions and some types of bit damage. It was therefore augmented with bit images for which the type of failure was determined through analysis by a subject- matter expert. A classifier was subsequently developed which properly identified 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 method. The automated forensics approach to Polycrystalline Diamond Compact (PDC) bit damage root cause analysis described in this paper can be performed using 2D bit photos that can be easily captured on a phone or camera at the rig site. By identifying the potential root causes of PDC damage through image processing, drilling parameters and bit selection can be optimized to prolong future bit life. The algorithm also enables uniformity in bit analysis across a company's operations, as well as the standardization of the process.

Drilling dysfunction causes premature failure of bits and motors in hard formations. Dysfunctions may be influenced by; bit design, bottom hole assembly (BHA) design, rig control systems, connection practices, and rotating head use. Sensors that record weight, torque, and vibration in the bit can offer insights that are not detectable further up the BHA. By understanding the root causes before the next bit run, it is possible to rapidly improve performance and prolong bit life. The formation being drilled in this study is a hard extremely abrasive shale, requiring 35+ runs per lateral section. The primary cause of polycrystalline diamond cutter (PDC) failure was smooth wear and thermal damage. The wear flats are attributed to abrasion and mechanical chipping that rapidly progress to thermal damage. Higher weights were not effective and it was hypothesized that buckling was occurring, causing insufficient weight transfer and increased lateral vibration. In-bit sensors that measure weight, torque, revolutions per minute (RPM), and lateral, axial and torsional vibration were run in hole to evaluate the weight transfer issues and dysfunction. High frequency downhole and surface data were combined with forensic images of the bit and BHA to confirm the weight transfer issues. In total, three major problems were identified and rectified during this study: drill string buckling, rate of penetration (ROP) loss due to the use of rotating control devices (RCDs) and WOB and differential pressure (DIFP) tare inconsistencies. Drill string buckling resulted in the downhole WOB being much less than surface WOB (DWOB<<SWOB) in early runs. Heavy weight drill pipe (HWDP) was run across the buckling zone to correct this. Subsequent runs showed a significant improvement in DWOB, reduction in lateral bit vibration, and improved performance and dull condition. Significant decreases in DWOB, DIFP, and ROP were noted when running tool joints through the RCD. Although observed before, in-bit accelerometers showed an increased lateral vibration that was a result of the loss in ROP and this continued long after the ROP recovered. DWOB and downhole torque (DTOR) were often much higher than SWOB and DIFP (converted to torque). Plots of hookload and stand pipe pressure tare values were used as indicators of inconsistent tares. Although premature motor failure were not noted in these runs, premature PDC cutter failure were. High frequency in-bit load sensing was used to identify persistent lateral vibration after a ROP loss event due to tool joints interacting with RCDs. A team based, continuous improvement, process was used to evaluate the root cause of downhole dysfunction and recommend bit/BHA design and operating procedure changes before the next bit was on bottom. This rapid analysis and joint recommendation process significantly prolonged bit life and improved drilling performance.