ISSN 2096-4498
CN 44-1745/U
Tunnel Construction ›› 2021, Vol. 41 ›› Issue (S1): 161-.DOI: 10.3973/j.issn.2096-4498.2021.S1.020
Previous Articles Next Articles
WANG Heng
Online:
Published:
Abstract: In order to predict the front geological conditions in real time during boring, the structural characteristics of traditional neural network model are analyzed based on the slag pictures of practical projects and an autonomous lightweight network model is designed. After training with slag pictures, the parameters of Mobilenet lightweight network model is adjusted with the data. The results show that: (1) With excess parameters and memory, the traditional neural network algorithm cannot deploy the edge terminal of slag recognition onsite, while the selfdesigned lightweight network can meet the accuracy requirements of onsite slag image classification. (2) The classification accuracy of Mobilenet lightweight network model reaches 97%, but its calculation amount is only 80%~90% of the amount of traditional neural network model.
Key words: TBM, convolutional neural network, rock slag classification, slagging system, lightweight model, AlexNet network model, VGG network model, Mobilenet model
CLC Number:
U 45
WANG Heng. Research on Lightweight Algorithm for Edge Terminal of Rock Slag Classification[J]. Tunnel Construction, 2021, 41(S1): 161-.
0 / / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.suidaojs.com/EN/10.3973/j.issn.2096-4498.2021.S1.020
http://www.suidaojs.com/EN/Y2021/V41/IS1/161
Key Technology and Application of Efficient Tunneling of an Extra-Long Tunnel Bored by Two Tunnel Boring Machines
TBM Selection and Key Technologies of Qiandao Lake Water Distribution Project
Study and Practice on Negative Ring Launching Technique for DoubleShield TBM Used in Qingdao Metro
Discussion on Construction Technology for Mode Conversion between Earth Pressure Balance and SingleShield TBM of DoubleMode Shield
川藏铁路隧道TBM适应性选型分析及不良地质对策与思考
Design and Application of a Compact TBM for an Ultrasmall Turning Radius: a Case Study on a Drainage Gallery Tunnel Project of
Wendeng Pumped Storage Power Station in Shandong, China