Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning

The automatic discrimination of rock fracture and blast events is complex and challenging due to the similar waveform characteristics. To solve this problem, a new method based on the signal complexity analysis and machine learning has been proposed in this paper. First, the permutation entropy valu...

Full description

Saved in:
Bibliographic Details
Main Authors: Zilong Zhou, Ruishan Cheng, Xin Cai, Dan Ma, Chong Jiang
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2018/9753028
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850110452333281280
author Zilong Zhou
Ruishan Cheng
Xin Cai
Dan Ma
Chong Jiang
author_facet Zilong Zhou
Ruishan Cheng
Xin Cai
Dan Ma
Chong Jiang
author_sort Zilong Zhou
collection DOAJ
description The automatic discrimination of rock fracture and blast events is complex and challenging due to the similar waveform characteristics. To solve this problem, a new method based on the signal complexity analysis and machine learning has been proposed in this paper. First, the permutation entropy values of signals at different scale factors are calculated to reflect complexity of signals and constructed into a feature vector set. Secondly, based on the feature vector set, back-propagation neural network (BPNN) as a means of machine learning is applied to establish a discriminator for rock fracture and blast events. Then to evaluate the classification performances of the new method, the classifying accuracies of support vector machine (SVM), naive Bayes classifier, and the new method are compared, and the receiver operating characteristic (ROC) curves are also analyzed. The results show the new method obtains the best classification performances. In addition, the influence of different scale factor q and number of training samples n on discrimination results is discussed. It is found that the classifying accuracy of the new method reaches the highest value when q = 8–15 or 8–20 and n=140.
format Article
id doaj-art-461cbf98dec74607a0f335970067dd7b
institution OA Journals
issn 1070-9622
1875-9203
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-461cbf98dec74607a0f335970067dd7b2025-08-20T02:37:49ZengWileyShock and Vibration1070-96221875-92032018-01-01201810.1155/2018/97530289753028Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine LearningZilong Zhou0Ruishan Cheng1Xin Cai2Dan Ma3Chong Jiang4School of Resources and Safety Engineering, Central South University, Changsha 410000, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410000, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410000, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410000, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410000, ChinaThe automatic discrimination of rock fracture and blast events is complex and challenging due to the similar waveform characteristics. To solve this problem, a new method based on the signal complexity analysis and machine learning has been proposed in this paper. First, the permutation entropy values of signals at different scale factors are calculated to reflect complexity of signals and constructed into a feature vector set. Secondly, based on the feature vector set, back-propagation neural network (BPNN) as a means of machine learning is applied to establish a discriminator for rock fracture and blast events. Then to evaluate the classification performances of the new method, the classifying accuracies of support vector machine (SVM), naive Bayes classifier, and the new method are compared, and the receiver operating characteristic (ROC) curves are also analyzed. The results show the new method obtains the best classification performances. In addition, the influence of different scale factor q and number of training samples n on discrimination results is discussed. It is found that the classifying accuracy of the new method reaches the highest value when q = 8–15 or 8–20 and n=140.http://dx.doi.org/10.1155/2018/9753028
spellingShingle Zilong Zhou
Ruishan Cheng
Xin Cai
Dan Ma
Chong Jiang
Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning
Shock and Vibration
title Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning
title_full Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning
title_fullStr Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning
title_full_unstemmed Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning
title_short Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning
title_sort discrimination of rock fracture and blast events based on signal complexity and machine learning
url http://dx.doi.org/10.1155/2018/9753028
work_keys_str_mv AT zilongzhou discriminationofrockfractureandblasteventsbasedonsignalcomplexityandmachinelearning
AT ruishancheng discriminationofrockfractureandblasteventsbasedonsignalcomplexityandmachinelearning
AT xincai discriminationofrockfractureandblasteventsbasedonsignalcomplexityandmachinelearning
AT danma discriminationofrockfractureandblasteventsbasedonsignalcomplexityandmachinelearning
AT chongjiang discriminationofrockfractureandblasteventsbasedonsignalcomplexityandmachinelearning