Optimized ANN model for predicting rock mass quality ahead of tunnel face using measure-while-drilling data

2021 ◽  
Author(s):  
Jiankang Liu ◽  
Yujing Jiang ◽  
Wei Han ◽  
Osamu Sakaguchi
Keyword(s):  
Rock Mass ◽  
Ann Model ◽  
Tunnel Face ◽  
Rock Mass Quality ◽  
Drilling Data

Multi-source data driven method for assessing the rock mass quality of a NATM tunnel face via hybrid ensemble learning models

2021 ◽  
Vol 147 ◽  
pp. 104914
Author(s):  
Mingliang Zhou ◽  
Jiayao Chen ◽  
Hongwei Huang ◽  
Dongming Zhang ◽  
Shuai Zhao ◽  
...  
Keyword(s):  
Rock Mass ◽  
Ensemble Learning ◽  
Data Driven ◽  
Learning Models ◽  
Tunnel Face ◽  
Rock Mass Quality ◽  
Source Data ◽  
Natm Tunnel

ethodical principles of designing the formation of rock mass quality for lump sorting scheelite-containing ores at the stage of mining

2019 ◽  
Vol 8 (29) ◽  
pp. 3-17
Author(s):  
V.A. Khakulov ◽  
◽  
V.A. Shapovalov ◽  
V.N. Ignatov ◽  
Zh.V. Karpova ◽  
...  
Keyword(s):  
Rock Mass ◽  
Rock Mass Quality

scholarly journals Weightage Effect during Back-Calculation of Rock-Mass Quality from the Installed Tunnel Support in Rock-Mass Rating and Tunneling Quality Index System

2019 ◽  
Vol 9 (10) ◽  
pp. 2065 ◽  
Author(s):  
Jonguk Kim ◽  
Hafeezur Rehman ◽  
Wahid Ali ◽  
Abdul Muntaqim Naji ◽  
Hankyu Yoo
Keyword(s):  
Rock Mass ◽  
Quality Index ◽  
Rock Bolt ◽  
Rock Mass Rating ◽  
Rock Mass Quality ◽  
Back Calculation ◽  
The Difference ◽  
Bolt Spacing ◽  
Q System ◽  
Selection Of

In extensively used empirical rock-mass classification systems, the rock-mass rating (RMR) and tunneling quality index (Q) system, rock-mass quality, and tunnel span are used for the selection of rock bolt length and spacing and shotcrete thickness. In both systems, the rock bolt spacing and shotcrete thickness selection are based on the same principle, which is used for the back-calculation of the rock-mass quality. For back-calculation, there is no criterion for the selection of rock-bolt-spacing-based rock-mass quality weightage and shotcrete thickness along with tunnel-span-based rock-mass quality weightage. To determine this weightage effect during the back-calculation, five weightage cases are selected, explained through example, and applied using published data. In the RMR system, the weightage effect is expressed in terms of the difference between the calculated and back-calculated rock-mass quality in the two versions of RMR. In the Q system, the weightage effect is presented in plots of stress reduction factor versus relative block size. The results show that the weightage effect during back-calculation not only depends on the difference in rock-bolt-spacing-based rock-mass quality and shotcrete along with tunnel-span-based rock-mass quality, but also on their corresponding values.

scholarly journals Joint Investigation and 3D Visual Evaluation of Rock Mass Quality

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Haiping Yuan ◽  
Chenghao Chen ◽  
Yixian Wang ◽  
Hanbing Bian ◽  
Yan Liu
Keyword(s):  
Rock Mass ◽  
Quality Evaluation ◽  
Evaluation Method ◽  
Three Dimensional ◽  
Rock Mass Classification ◽  
National Standard ◽  
Ratio Method ◽  
Rock Mass Quality ◽  
Close Range ◽  
Mass Classification

In order to realize the high efficiency quality classification and three-dimensional visualization of engineering rock mass and to solve the technical difficulties of the traditional rock mass quality evaluation method such as high labor intensity, long process time consumption, many intervention processes such as scale measurement and manual calculation, and nonintuitive classification results, this paper puts forward a 3D visual rock mass quality evaluation method and system based on close-range photography, which optimizes the traditional rock mass quality evaluation method, makes the rock mass classification three-dimensional and visible, and realizes the estimation of unrevealed rock mass quality evaluation index. The research results show the following: (1) The method of storing joint information by close-range photography and extracting joint information by human-computer interaction improves the working efficiency and the process is safe and controllable compared with the traditional method of collecting fracture parameters. (2) Based on the statistical analysis of 97 groups of roadway survey data, the comprehensive statistical regression formula between BQ value of Chinese national standard and RMR value is given, and there is a good correlation between BQ value and RMR value of rock mass quality index. (3) Based on the power-inverse ratio method, the three-dimensional model of rock mass classification of the mine was established, and the cutting model obtained the current distribution diagram of rock mass quality grade, providing scientific reference for drilling, blasting, support, and other production design optimizations.

Assessment of the Excavatability of Rock Based on Rock Mass Quality: A Case Study from India

2018 ◽  
Vol 36 (6) ◽  
pp. 4015-4027 ◽  
Author(s):  
A. K. Naithani ◽  
D. S. Rawat ◽  
L. G. Singh ◽  
Prasnna Jain
Keyword(s):  
Rock Mass ◽  
Rock Mass Quality

Coal identification using neural networks with real-time coalbed methane drilling data

2019 ◽  
Vol 59 (1) ◽  
pp. 319 ◽  
Author(s):  
Ruizhi Zhong ◽  
Raymond Johnson Jr ◽  
Zhongwei Chen ◽  
Nathaniel Chand
Keyword(s):  
Real Time ◽  
Coalbed Methane ◽  
Gamma Ray ◽  
Ann Model ◽  
Drilling Data ◽  
Weight On Bit ◽  
Net To Gross ◽  
Rotary Speed ◽  
Artificial Neural Network Ann ◽  
Log Interpretation

Currently, coal is identified using coring data or log interpretation. Coring is the most dependable methodology, but it is costly and its characterisation is expensive and time consuming. Logging methods are convenient, reliable, and reproducible, but can be subject to statistical and shouldering effects and often have operational difficulties in deviated or horizontal wells. Drilling data, which are routinely available, can potentially be used to identify coal sections in a machine learning environment when conventional wireline logs are not available. To achieve this, a four-layer artificial neural network (ANN) was used to identify coals in a well at Walloon Sub-Group, Surat Basin. The ANN model used drilling data and some logging-while-drilling (LWD) data. The inputs for the lithological model from high-frequency drilling data include weight on bit, rotary speed, torque, and rate of penetration. Inputs from LWD data include gamma ray and hole diameter. The criterion for coal identification is based on bulk density cutoff. The simulation results show that the ANN can deliver an overall accuracy of 96%. Due to the low net-to-gross ratio of coals within the Walloon sequence, a lower but reasonable F1 score of 0.78 is achievable for the coal sections. The proposed model can potentially be implemented in real-time to identify coal intervals without additional logs and aid validation of minimal log data.

Sign in / Sign up

Export Citation Format

Share Document