Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform

This study employs the mechanical vibration and acoustic waves of a hydraulic support tail beam for an accurate and fast coal-rock recognition. The study proposes a diagnosis method based on bimodal deep learning and Hilbert-Huang transform. The bimodal deep neural networks (DNN) adopt bimodal learn...

Full description

Saved in:
Bibliographic Details
Main Authors: Guoxin Zhang, Zengcai Wang, Lei Zhao, Yazhou Qi, Jinshan Wang
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2017/3809525
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849403769866944512
author Guoxin Zhang
Zengcai Wang
Lei Zhao
Yazhou Qi
Jinshan Wang
author_facet Guoxin Zhang
Zengcai Wang
Lei Zhao
Yazhou Qi
Jinshan Wang
author_sort Guoxin Zhang
collection DOAJ
description This study employs the mechanical vibration and acoustic waves of a hydraulic support tail beam for an accurate and fast coal-rock recognition. The study proposes a diagnosis method based on bimodal deep learning and Hilbert-Huang transform. The bimodal deep neural networks (DNN) adopt bimodal learning and transfer learning. The bimodal learning method attempts to learn joint representation by considering acceleration and sound pressure modalities, which both contribute to coal-rock recognition. The transfer learning method solves the problem regarding DNN, in which a large number of labeled training samples are necessary to optimize the parameters while the labeled training sample is limited. A suitable installation location for sensors is determined in recognizing coal-rock. The extraction features of acceleration and sound pressure signals are combined and effective combination features are selected. Bimodal DNN consists of two deep belief networks (DBN), each DBN model is trained with related samples, and the parameters of the pretrained DBNs are transferred to the final recognition model. Then the parameters of the proposed model are continuously optimized by pretraining and fine-tuning. Finally, the comparison of experimental results demonstrates the superiority of the proposed method in terms of recognition accuracy.
format Article
id doaj-art-8305ec654c6d4cd0bab8ebd7840245eb
institution Kabale University
issn 1070-9622
1875-9203
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-8305ec654c6d4cd0bab8ebd7840245eb2025-08-20T03:37:11ZengWileyShock and Vibration1070-96221875-92032017-01-01201710.1155/2017/38095253809525Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang TransformGuoxin Zhang0Zengcai Wang1Lei Zhao2Yazhou Qi3Jinshan Wang4School of Mechanical Engineering, Shandong University, No. 17923 Jingshi Road, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, No. 17923 Jingshi Road, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, No. 17923 Jingshi Road, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, No. 17923 Jingshi Road, Jinan 250061, ChinaSchool of Mechanical Engineering, Shandong University, No. 17923 Jingshi Road, Jinan 250061, ChinaThis study employs the mechanical vibration and acoustic waves of a hydraulic support tail beam for an accurate and fast coal-rock recognition. The study proposes a diagnosis method based on bimodal deep learning and Hilbert-Huang transform. The bimodal deep neural networks (DNN) adopt bimodal learning and transfer learning. The bimodal learning method attempts to learn joint representation by considering acceleration and sound pressure modalities, which both contribute to coal-rock recognition. The transfer learning method solves the problem regarding DNN, in which a large number of labeled training samples are necessary to optimize the parameters while the labeled training sample is limited. A suitable installation location for sensors is determined in recognizing coal-rock. The extraction features of acceleration and sound pressure signals are combined and effective combination features are selected. Bimodal DNN consists of two deep belief networks (DBN), each DBN model is trained with related samples, and the parameters of the pretrained DBNs are transferred to the final recognition model. Then the parameters of the proposed model are continuously optimized by pretraining and fine-tuning. Finally, the comparison of experimental results demonstrates the superiority of the proposed method in terms of recognition accuracy.http://dx.doi.org/10.1155/2017/3809525
spellingShingle Guoxin Zhang
Zengcai Wang
Lei Zhao
Yazhou Qi
Jinshan Wang
Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform
Shock and Vibration
title Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform
title_full Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform
title_fullStr Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform
title_full_unstemmed Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform
title_short Coal-Rock Recognition in Top Coal Caving Using Bimodal Deep Learning and Hilbert-Huang Transform
title_sort coal rock recognition in top coal caving using bimodal deep learning and hilbert huang transform
url http://dx.doi.org/10.1155/2017/3809525
work_keys_str_mv AT guoxinzhang coalrockrecognitionintopcoalcavingusingbimodaldeeplearningandhilberthuangtransform
AT zengcaiwang coalrockrecognitionintopcoalcavingusingbimodaldeeplearningandhilberthuangtransform
AT leizhao coalrockrecognitionintopcoalcavingusingbimodaldeeplearningandhilberthuangtransform
AT yazhouqi coalrockrecognitionintopcoalcavingusingbimodaldeeplearningandhilberthuangtransform
AT jinshanwang coalrockrecognitionintopcoalcavingusingbimodaldeeplearningandhilberthuangtransform