Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM

Abstract Rotary percussion drills, specifically top hammer types, are essential in resource extraction and exploration. These drills frequently suffer damage at the drill bit, necessitating effective decision-making to address issues. Traditionally, on-site operators relied on intuition, but recent...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuna Nakazawa, Natsuo Okada, Jo Sasaki, Lesego Senjoba, Yoko Ohtomo, Youhei Kawamura
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Discover Applied Sciences
Subjects:
Online Access:https://doi.org/10.1007/s42452-025-06796-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726256439885824
author Yuna Nakazawa
Natsuo Okada
Jo Sasaki
Lesego Senjoba
Yoko Ohtomo
Youhei Kawamura
author_facet Yuna Nakazawa
Natsuo Okada
Jo Sasaki
Lesego Senjoba
Yoko Ohtomo
Youhei Kawamura
author_sort Yuna Nakazawa
collection DOAJ
description Abstract Rotary percussion drills, specifically top hammer types, are essential in resource extraction and exploration. These drills frequently suffer damage at the drill bit, necessitating effective decision-making to address issues. Traditionally, on-site operators relied on intuition, but recent advancements promote automated diagnostic systems to enhance safety and failure detection in challenging mining environments, such as those with high dust levels and intense vibrations. This study uses Convolutional Neural Networks (CNN) to develop an automated diagnostic system for detecting drill bit abnormalities. Previous models classified five distinct bit conditions but faced challenges in generalizing performance due to variations in the frequency bands used for judgments. This study refines the approach by simplifying the system to detect two states: normal and abnormal. Using Gradient-weighted Class Activation Mapping (Grad-CAM), the system identifies critical frequency bands, enabling a unified frequency filter. By training the model to recognize differences in rock types, it adapts to untrained drill bit types, achieving an accuracy of 83.3%, significantly higher than the 44.8% in previous models. This innovation allows the system to generalize across different rock and bit conditions, improving drilling efficiency and minimizing downtime in diverse environments.
format Article
id doaj-art-c59ca19bb9ad406999cbc4859bbf8c65
institution DOAJ
issn 3004-9261
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Discover Applied Sciences
spelling doaj-art-c59ca19bb9ad406999cbc4859bbf8c652025-08-20T03:10:13ZengSpringerDiscover Applied Sciences3004-92612025-04-017411710.1007/s42452-025-06796-7Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAMYuna Nakazawa0Natsuo Okada1Jo Sasaki2Lesego Senjoba3Yoko Ohtomo4Youhei Kawamura5Division of Sustainable Resources Engineering, Graduate School of Engineering, Hokkaido UniversityDivision of Sustainable Resources Engineering, Graduate School of Engineering, Hokkaido UniversityMMC RYOTEC Co. Ltd.Graduate School of International Resource Sciences, Akita UniversityDivision of Sustainable Resources Engineering, Faculty of Engineering, Hokkaido UniversityDivision of Sustainable Resources Engineering, Faculty of Engineering, Hokkaido UniversityAbstract Rotary percussion drills, specifically top hammer types, are essential in resource extraction and exploration. These drills frequently suffer damage at the drill bit, necessitating effective decision-making to address issues. Traditionally, on-site operators relied on intuition, but recent advancements promote automated diagnostic systems to enhance safety and failure detection in challenging mining environments, such as those with high dust levels and intense vibrations. This study uses Convolutional Neural Networks (CNN) to develop an automated diagnostic system for detecting drill bit abnormalities. Previous models classified five distinct bit conditions but faced challenges in generalizing performance due to variations in the frequency bands used for judgments. This study refines the approach by simplifying the system to detect two states: normal and abnormal. Using Gradient-weighted Class Activation Mapping (Grad-CAM), the system identifies critical frequency bands, enabling a unified frequency filter. By training the model to recognize differences in rock types, it adapts to untrained drill bit types, achieving an accuracy of 83.3%, significantly higher than the 44.8% in previous models. This innovation allows the system to generalize across different rock and bit conditions, improving drilling efficiency and minimizing downtime in diverse environments.https://doi.org/10.1007/s42452-025-06796-7Rotary percussion drillConvolutional neural networkGrad-CAMDrill bit abnormalityFrequency filterMining automation
spellingShingle Yuna Nakazawa
Natsuo Okada
Jo Sasaki
Lesego Senjoba
Yoko Ohtomo
Youhei Kawamura
Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM
Discover Applied Sciences
Rotary percussion drill
Convolutional neural network
Grad-CAM
Drill bit abnormality
Frequency filter
Mining automation
title Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM
title_full Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM
title_fullStr Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM
title_full_unstemmed Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM
title_short Improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad-CAM
title_sort improvement of generalization performance of diagnostic system for drill bit abnormality in rotary percussion drilling with grad cam
topic Rotary percussion drill
Convolutional neural network
Grad-CAM
Drill bit abnormality
Frequency filter
Mining automation
url https://doi.org/10.1007/s42452-025-06796-7
work_keys_str_mv AT yunanakazawa improvementofgeneralizationperformanceofdiagnosticsystemfordrillbitabnormalityinrotarypercussiondrillingwithgradcam
AT natsuookada improvementofgeneralizationperformanceofdiagnosticsystemfordrillbitabnormalityinrotarypercussiondrillingwithgradcam
AT josasaki improvementofgeneralizationperformanceofdiagnosticsystemfordrillbitabnormalityinrotarypercussiondrillingwithgradcam
AT lesegosenjoba improvementofgeneralizationperformanceofdiagnosticsystemfordrillbitabnormalityinrotarypercussiondrillingwithgradcam
AT yokoohtomo improvementofgeneralizationperformanceofdiagnosticsystemfordrillbitabnormalityinrotarypercussiondrillingwithgradcam
AT youheikawamura improvementofgeneralizationperformanceofdiagnosticsystemfordrillbitabnormalityinrotarypercussiondrillingwithgradcam