Application of convolutional neural network to defect diagnosis of drill bits
Drilling, one of the most used machining processes, has wide application in different industrial fields. Monitoring the system health and operation status of the drilling process is essential for maintaining production efficiency. In this study, a convolutional neural network (CNN), a deep-learning...
| Prif Awduron: | , , , |
|---|---|
| Awduron Eraill: | |
| Fformat: | Journal Article |
| Iaith: | English |
| Cyhoeddwyd: |
2023
|
| Pynciau: | |
| Mynediad Ar-lein: | https://hdl.handle.net/10356/165203 |
| _version_ | 1826118071179280384 |
|---|---|
| author | Yu, Yongchao Liu, Qi Han, Boon Siew Zhou, Wei |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Yu, Yongchao Liu, Qi Han, Boon Siew Zhou, Wei |
| author_sort | Yu, Yongchao |
| collection | NTU |
| description | Drilling, one of the most used machining processes, has wide application in different industrial fields. Monitoring the system health and operation status of the drilling process is essential for maintaining production efficiency. In this study, a convolutional neural network (CNN), a deep-learning method, is applied to the defect diagnosis of drill bits. Four drill bits with different health conditions were used to drill holes in an aluminum block, and a vibration sensor collected the signals. Vibration spectrograms generated using short-time Fourier transform were applied to a 2D CNN algorithm, and they were then reconstructed into a 1D data set and applied to a 1D CNN algorithm. The input data size was reduced significantly compared to the raw vibration data after the data-reconstruction process. As a result, the 2D CNN process shows a diagnostic accuracy of 97.33%. On the other hand, the 1D CNN provides a diagnostic accuracy of 96.6%, but it only requires 2/3 of the computational time required by the 2D CNN. |
| first_indexed | 2024-10-01T04:37:25Z |
| format | Journal Article |
| id | ntu-10356/165203 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:37:25Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1652032023-03-25T16:48:08Z Application of convolutional neural network to defect diagnosis of drill bits Yu, Yongchao Liu, Qi Han, Boon Siew Zhou, Wei School of Mechanical and Aerospace Engineering Engineering::Mechanical engineering Defect Diagnosis Convolutional Neural Network Drilling, one of the most used machining processes, has wide application in different industrial fields. Monitoring the system health and operation status of the drilling process is essential for maintaining production efficiency. In this study, a convolutional neural network (CNN), a deep-learning method, is applied to the defect diagnosis of drill bits. Four drill bits with different health conditions were used to drill holes in an aluminum block, and a vibration sensor collected the signals. Vibration spectrograms generated using short-time Fourier transform were applied to a 2D CNN algorithm, and they were then reconstructed into a 1D data set and applied to a 1D CNN algorithm. The input data size was reduced significantly compared to the raw vibration data after the data-reconstruction process. As a result, the 2D CNN process shows a diagnostic accuracy of 97.33%. On the other hand, the 1D CNN provides a diagnostic accuracy of 96.6%, but it only requires 2/3 of the computational time required by the 2D CNN. Agency for Science, Technology and Research (A*STAR) Published version This research is funded by the Agency for Science, Technology, and Research (A*STAR) and Schaeffler for project entitled “Condition Monitoring and Fault Prognosis of Robot Joints based on Fiber Optic Sensing and Deep Learning” through grants #020956-00003 and #021003-00003. 2023-03-20T05:10:46Z 2023-03-20T05:10:46Z 2022 Journal Article Yu, Y., Liu, Q., Han, B. S. & Zhou, W. (2022). Application of convolutional neural network to defect diagnosis of drill bits. Applied Sciences, 12(21), 10799-. https://dx.doi.org/10.3390/app122110799 2076-3417 https://hdl.handle.net/10356/165203 10.3390/app122110799 2-s2.0-85141857180 21 12 10799 en #020956-00003 #021003-00003 Applied Sciences © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). application/pdf |
| spellingShingle | Engineering::Mechanical engineering Defect Diagnosis Convolutional Neural Network Yu, Yongchao Liu, Qi Han, Boon Siew Zhou, Wei Application of convolutional neural network to defect diagnosis of drill bits |
| title | Application of convolutional neural network to defect diagnosis of drill bits |
| title_full | Application of convolutional neural network to defect diagnosis of drill bits |
| title_fullStr | Application of convolutional neural network to defect diagnosis of drill bits |
| title_full_unstemmed | Application of convolutional neural network to defect diagnosis of drill bits |
| title_short | Application of convolutional neural network to defect diagnosis of drill bits |
| title_sort | application of convolutional neural network to defect diagnosis of drill bits |
| topic | Engineering::Mechanical engineering Defect Diagnosis Convolutional Neural Network |
| url | https://hdl.handle.net/10356/165203 |
| work_keys_str_mv | AT yuyongchao applicationofconvolutionalneuralnetworktodefectdiagnosisofdrillbits AT liuqi applicationofconvolutionalneuralnetworktodefectdiagnosisofdrillbits AT hanboonsiew applicationofconvolutionalneuralnetworktodefectdiagnosisofdrillbits AT zhouwei applicationofconvolutionalneuralnetworktodefectdiagnosisofdrillbits |