Neural network technology for strata strength characterization

Utt, Walter K.

doi:10.1109/ijcnn.1999.830760

Cited by 18 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system combined the monitoring and control features of the earlier drills and added vibration analysis, and could use off-the-shelf controllers and data acquisition systems. Utt (1999) and Utt et al (2002a) applied neural network technology to the classification of mine roof strata in terms of relative strength. In this project, the feasibility of using a monitoring system on a roof drill to assess the integrity of a mine roof and warn the roof drill operator when a weak layer was to be encountered was studied.…”

Section: Rock Mass Classification By Using Borehole Probingmentioning

confidence: 99%

Review of Ground Characterization by Using Instrumented Drills for Underground Mining and Construction

2015

View full text Add to dashboard Cite

In underground mining, many miners are injured or lose their lives because of roof/pillar instability each year, and this is a persistent safety risk. Characterization of overlying strata is important for the design of safe and cost-effective ground support systems. Entry roof characterization can be performed by geological backmapping of the ground using various methods such as geophysical logging, borescoping, rock mass rating, and intelligent roof bolt drilling systems. This paper offers a brief review of mine roof characterization methods, followed by an introduction to and discussion of roof characterization methods using instrumented roof bolters. A brief overview of the various instrumentation systems developed for roof bolt drills is presented. The results of the preliminary study and initial testing indicate that, despite recent improvements in the area of ground characterization by instrumented drills, there are still several issues that must be addressed to improve the efficiency and accuracy of existing systems. A summary of suggested improvements is provided.

show abstract

Section: Rock Mass Classification By Using Borehole Probingmentioning

confidence: 99%

Review of Ground Characterization by Using Instrumented Drills for Underground Mining and Construction

2015

View full text Add to dashboard Cite

show abstract

“…In the studies carried out in the iron ore opencast mine [20,21], the penetration coefficient was used together with the unit cutting energy to monitor the efficiency of the drilling process. The results of the MWD method were analyzed with the use of neural networks [29,30], as a basis for the classification of rock strength. In this case, the main goal was to develop a method of alerting the working drill operator to the risk of weakened rock layers.…”

Section: Technological Methods Based On the Borehole Drilling Processmentioning

confidence: 99%

Identification of Rock Mass Critical Discontinuities While Borehole Drilling

et al. 2021

View full text Add to dashboard Cite

Modern technologies need more mineral resources for energy generation, metallurgical products, chemicals, and many other uses. These resources are usually extracted from the Earth’s crust. Many engineering underground-space infrastructures are left after mining activity, with their very interesting features such as very large storage capacities (e.g., for hydrocarbons, hydrogen, radioactive, or other waste), and long-term geomechanical stability. Our original experiments were carried out in the conditions of an underground metal ore mine where typical mobile drilling rigs, additionally equipped with a set of sensors for recording signals as effects of rock–drill interaction were used for the research testing. A series of boreholes with diameters of Ø38 and lengths of up to 9 m in the rock medium were drilled in the “weak” and “strong” rock masses, and the frequency spectra of their signals were analyzed with the use of the fast Fourier transform (FFT) and short-time Fourier transform (STFT) algorithms. According to the proposed idealized theoretical model of the disturbance and the distinctive acceleration value of the drilling characteristic, the location of the critical discontinuities in the roof of the excavation were recognized. The most important advantage of the proposed method is the quantity and objective monitoring method for detection of a critical rock mass defect (discontinuity) that is significant for the potential functionality of underground workings as a potential energy storage room and their reinforcement.

show abstract

“…In the field of satellite remote sensing, neural networks were used for the determination of different lithological regions (Hafner and Komac, 1998). There are some other works dealing with ore and rock characterisation (Cutmore et al, 1997;Millar and Hudson, 1994;Utt, 1999). Neural network can also serve as a tool which helps to determine the relative importance of the factors influencing the stability of underground objects according to their importance (Yang and Zhang, 1997).…”

Section: Use Of Neural Network In Miningmentioning

confidence: 99%

Prediction of subsidence due to underground mining by artificial neural networks

Ambrožič

Turk

2003

Computers & Geosciences

101

View full text Add to dashboard Cite

Alternatively to empirical prediction methods, methods based on influential functions and methods based on mechanical model, artificial neural networks can be used for the the surface subsidence prediction. In our case, the multi-layer feed-forward neural network was used. The training and testing of neural network is based on available data. Input variables represent extraction parameters and coordinates of the points of interest, while the output variable represents surface subsidence data. After the neural network has been successfully trained, its performance is tested on a separate testing set. Finally, the surface subsidence trough above the projected excavation is predicted by the trained neural network. The applicability of artificial neural network for the prediction of surface subsidence was verified in different subsidence models and proved on actual excavated levels and in levelled data on surface profile points in the Velenje Coal Mine.

show abstract

Neural network technology for strata strength characterization

Cited by 18 publications

References 4 publications

Review of Ground Characterization by Using Instrumented Drills for Underground Mining and Construction

Review of Ground Characterization by Using Instrumented Drills for Underground Mining and Construction

Identification of Rock Mass Critical Discontinuities While Borehole Drilling

Prediction of subsidence due to underground mining by artificial neural networks

Contact Info

Product

Resources

About