Monitoring blasting events in an underground mine with artificial intelligence techniques
© 2017 International Society for Structural Health Monitoring of Intelligent Infrastrucure. All rights reserved. This paper proposes to use Convolutional Neural Network (CNN) to identify the Time Delay of Arrival (TDOA) and subsequently the source location of micro-seismic events. For any two sensor...
| Main Authors: | , , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2017
|
| Online Access: | http://hdl.handle.net/20.500.11937/70260 |
| _version_ | 1848762257442340864 |
|---|---|
| author | Huang, L. Li, Jun Hao, Hong Li, X. |
| author_facet | Huang, L. Li, Jun Hao, Hong Li, X. |
| author_sort | Huang, L. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | © 2017 International Society for Structural Health Monitoring of Intelligent Infrastrucure. All rights reserved. This paper proposes to use Convolutional Neural Network (CNN) to identify the Time Delay of Arrival (TDOA) and subsequently the source location of micro-seismic events. For any two sensor waveforms recorded from the same event, the cross wavelet transform power and phase spectra, and the corresponding output function values can be obtained. They will be treated as the input and output of the CNN model for training. The measured data from eight blasting tests in an underground mine are used to test the trained CNN model and identify the location of the conducted blasting test. The exact locations of these in-field blasting tests are available in prior and will be taken as the references for demonstrating the accuracy of the proposed approach. Results demonstrate the accuracy of using the proposed approach in identifying the in-field blasting event locations. |
| first_indexed | 2025-11-14T10:44:42Z |
| format | Conference Paper |
| id | curtin-20.500.11937-70260 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:44:42Z |
| publishDate | 2017 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-702602018-08-08T04:44:12Z Monitoring blasting events in an underground mine with artificial intelligence techniques Huang, L. Li, Jun Hao, Hong Li, X. © 2017 International Society for Structural Health Monitoring of Intelligent Infrastrucure. All rights reserved. This paper proposes to use Convolutional Neural Network (CNN) to identify the Time Delay of Arrival (TDOA) and subsequently the source location of micro-seismic events. For any two sensor waveforms recorded from the same event, the cross wavelet transform power and phase spectra, and the corresponding output function values can be obtained. They will be treated as the input and output of the CNN model for training. The measured data from eight blasting tests in an underground mine are used to test the trained CNN model and identify the location of the conducted blasting test. The exact locations of these in-field blasting tests are available in prior and will be taken as the references for demonstrating the accuracy of the proposed approach. Results demonstrate the accuracy of using the proposed approach in identifying the in-field blasting event locations. 2017 Conference Paper http://hdl.handle.net/20.500.11937/70260 restricted |
| spellingShingle | Huang, L. Li, Jun Hao, Hong Li, X. Monitoring blasting events in an underground mine with artificial intelligence techniques |
| title | Monitoring blasting events in an underground mine with artificial intelligence techniques |
| title_full | Monitoring blasting events in an underground mine with artificial intelligence techniques |
| title_fullStr | Monitoring blasting events in an underground mine with artificial intelligence techniques |
| title_full_unstemmed | Monitoring blasting events in an underground mine with artificial intelligence techniques |
| title_short | Monitoring blasting events in an underground mine with artificial intelligence techniques |
| title_sort | monitoring blasting events in an underground mine with artificial intelligence techniques |
| url | http://hdl.handle.net/20.500.11937/70260 |