You Only Look Twice! for Failure Causes Identification of Drill Bits

TL;DR

This study develops an automated image-based system using YOLO models and decision trees to accurately identify drill bit failure causes, significantly aiding maintenance and operational safety.

Contribution

It introduces a novel integrated pipeline combining YOLO detection and rule-based classification for precise failure cause identification from drill bit images.

Findings

High accuracy in cutter location detection (0.97 mPA)

Effective damage detection with 0.49 mPA score

Complete failure cause identification on test set

Abstract

Efficient identification of the root causes of drill bit failure is crucial due to potential impacts such as operational losses, safety threats, and delays. Early recognition of these failures enables proactive maintenance, reducing risks and financial losses associated with unforeseen breakdowns and prolonged downtime. Thus, our study investigates various causes of drill bit failure using images of different blades. The process involves annotating cutters with their respective locations and damage types, followed by the development of two YOLO Location and Damage Cutter Detection models, as well as multi-class multi-label Decision Tree and Random Forests models to identify the causes of failure by assessing the cutters' location and damage type. Additionally, RRFCI is proposed for the classification of failure causes. Notably, the cutter location detection model achieved a high score of 0.97 mPA, and the cutter damage detection model yielded a 0.49 mPA. The rule-based approach over-performed both DT and RF in failure cause identification, achieving a macro-average F1-score of 0.94 across all damage causes. The integration of the complete automated pipeline successfully identified 100\% of the 24 failure causes when tested on independent sets of ten drill bits, showcasing its potential to efficiently assist experts in identifying the root causes of drill bit damages.