Skip to main content
SpringerLink
Log in

Prediction Model of Longwall Powered Support Capacity Using Field Monitored Data of a Longwall Panel and Uncertainty-Based Neural Network

Geotechnical and Geological Engineering volume 34, pages 2033–2052 (2016)Cite this article

Abstract

Failure of longwall projects in India is attributed to many factors, one among them is the selection of under-rated capacity of powered support. It is evident with the catastrophic failures at longwall project of Kothadih in 1997, Charcha west in 1989 and Dhemomen in 1998 or increase in the existing capacity of the powered support at Balrampur and Rajendra longwall projects of SECL and PVK and GDK-10A mines of SCCL just after their installation. The mining or geotechnical engineers, researchers, mine management, planners and the government agencies are striving hard since the inception of mechanized longwall technology in Indian subcontinent. Therefore, proper understanding of pressure on longwall support is very much essential for accurate selection of power support for longwall panel. In this paper, Bayesian neural network (BNN) model is developed for estimation of leg pressure and associated uncertainty. The 396 data sets from seven longwall panels are collected which includes depth of working, height of extraction, main roof thickness, face retreat distance, overhung length behind powered support and leg pressure of hydraulic powered support. The leg pressure developed in a hydraulic powered support is a manifestation of the various geo-mining parameters and therefore functional relationship exists between them. The results from BNN are compared with the Levenberg–Marquardt neural network and linear regression and found that BNN applied for prediction of leg pressure perform better than the other two approaches. The developed model can be used to predict the leg pressure and hence powered support capacity for longwall projects.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

39,95 €

Price includes VAT (Finland)

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

References

  • Alehossein H, Poulsen BA (2009) Stress analysis of longwall top coal caving. Int J Rock Mech Min Sci 47:30–41

    Article  Google Scholar 

  • Bernardo JM, Smith AFM (1994) Bayesian theory, 1st edn. Wiley Publication, New York

    Book  Google Scholar 

  • Bishop CM (1996) Neural networks for pattern recognition, 1st edn. Oxford University Press, New York

    Google Scholar 

  • Castillo PA, Gonz´alez JJ, Merelo J, Rivas V, Romero G, Prieto A, Prop G (2000) Global optimization of multilayer perceptrons using gas. Neurocomputing 35:149–163

    Article  Google Scholar 

  • Chatterjee S, Bandopadhyay S (2011) Resource estimation of a placer gold deposit with uncertainty, applying the Bayesian neural network model. SME Trans 330:606–617

    Google Scholar 

  • Chatterjee S, Bandopadhyay S (2012) Reliability estimation using a genetic algorithm-based artificial neural network: an application to a load-haul-dump machine. Expert Syst Appl 39(12):10943–10951

    Article  Google Scholar 

  • Chatterjee S, Bandopadhyay S, Machuca D (2010) Ore grade prediction using genetic algorithm and clustering based ensemble neural network model. Math Geosci 42(3):309–326

    Article  Google Scholar 

  • Chen J (1998) Design of powered supports for longwall mining. PhD thesis. West Virginia University, Morgantown

  • Deb D, Kumar A, Rosha RPS (2006) Forecasting shield pressures at a longwall face using artificial neural networks. Int J Geotech Geol Eng 24:1021–1037

    Article  Google Scholar 

  • Denison D, Holmes C, Mallick B, Smith AFM (2002) Bayesian methods for nonlinear classification and regression, 1st edn. Wiley Publication, New York

    Google Scholar 

  • Elazar JP (1982) Multiple regression in behavioural research: explanation and prediction, 2nd edn. Holt, Rinehart and Winston, New York

    Google Scholar 

  • Hao X, Fan W, Shan z, Liu P (2015) An integrated approach for the prediction of underground-induced strata movement over longwall coal mining panels. Geot Geol Eng. doi:10.1007/s10706-015-9850-3

    Google Scholar 

  • Lawrence W (2009) A method for the design of longwall gate road roof support. Int J Rock Mech Min Sci 46:789–795

    Article  Google Scholar 

  • Lee C, Sterling R (1992) Identifying probable failure modes for underground openings using a neural network. Int J Rock Mech Min Sci Geomech Abstr 29:49–67

    Article  Google Scholar 

  • MacKay DJC (1992) A practical Bayesian framework for back propagation networks. Neural Comput 4(3):448–472

    Article  Google Scholar 

  • MacKay DJC (1999) Comparison of approximate methods for handling hyper parameters. Neural Comput 11(5):1035–1068

    Article  Google Scholar 

  • Maji VB, Sitaram YG (2008) Prediction of elastic modulus of jointed rock mass using artificial neural network. Int J Geotech Geol Eng 26:443–452

    Article  Google Scholar 

  • Montana DJ, Davis L (1989) Training feed-forward neural networks using genetic algorithms. In: Proceedings of 3rd international conference on genetic algorithms, San Francisco, USA, pp 762–767

  • Peng SS (1998) What can a shield leg pressure tell us? Coal Age 103:54–57

    Google Scholar 

  • Press WH, Teukolsky SA, Vetterling WT, Flannery BP (1992) Numerical recipes in C: the art of scientific computing, 2nd edn. Cambridge University Press, UK

    Google Scholar 

  • Radford MN (1996) Bayesian learning for neural networks (lecture notes in statistics). Springer, New York

    Google Scholar 

  • Rezaei M, Hossaini MF, Majdi A (2015) Determination of longwall mining-induced stress using the strain energy method. Rock Mech Rock Eng. doi:10.1007/s00603-014-0704-8

    Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    Article  Google Scholar 

  • Sakellariou MG, Ferentinou MD (2005) A study of slope stability prediction using neural networks. Int J Geotech Geol Eng 23:419–445

    Article  Google Scholar 

  • Trueman R, Lyman G, Callan M (2005a) Fitness for purpose longwall powered supports, Australian coal association research programme (ACARP), Project number C12007

  • Trueman R, Lyman G, Callan M, Robertson B (2005b) Assessing longwall support-roof interaction from shield leg pressure data. Min Technol 114:176–184

    Article  Google Scholar 

  • Trueman R, Lyman G, Cocker A (2009) Longwall roof control through a fundamental understanding of shield–strata interaction. Int J Rock Mech Min Sci 46:371–380

    Article  Google Scholar 

  • Vakili A, Hebblewhite BK (2010) A new cavability assessment criterion for longwall top coal caving. Int J Rock Mech Min Sci 47:1317–1329

    Article  Google Scholar 

  • Venkataramayya MS, Sudhakar L (2002) Selection of powered roof support for weak coal roof. J Mines Metals Fuels 50:114–117

    Google Scholar 

  • Verma AK, Deb D (2007a) Analysis of chock shield pressure using finite element method and face stability index. Min Technol 116(2):67–78

    Article  Google Scholar 

  • Verma AK, Deb D (2007b) Regression and neural regression approach for prediction of longwall chock-shield support pressure. In: Ribeiro e Sousa L, Olalla C, Grossmann N (eds) 11th congress of the ISRM, 09–13 July, Lisbon, Portugal, Taylor & Francis group, London, pp 1047–1052

  • Verma AK, Deb D (2010) Longwall face stability index for estimation of chock-shield pressure and face convergence. Int J Geotech Geol Eng 28:431–445

    Article  Google Scholar 

Download references

Acknowledgments

The results of this paper are based on a project funded under Fast Track Proposal for Young Scientists (approval no. SR/FTP/ETA-31/08) by Department of Science and Technology (Government of India). The authors are obliged to the colliery management for their valuable co-operation during the field observation. The views expressed in this paper are those of the authors and not necessarily of the institute to which they belong.

Author information

Authors and Affiliations

  1. Department of Mining Engineering, Indian Institute of Technology, Kharagpur, West Bengal, 721302, India

    Abhiram Kumar Verma

  2. Coal India Limited, CMPDIL, Singrauli, Madhya Pradesh, 486890, India

    Kaushal Kishore

  3. Department of Geological and Mining Engineering and Sciences, Michigan Technological University, Houghton, MI, 49931, USA

    Snehamoy Chatterjee

Authors
  1. Abhiram Kumar Verma
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kaushal Kishore
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Snehamoy Chatterjee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Abhiram Kumar Verma.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Verma, A.K., Kishore, K. & Chatterjee, S. Prediction Model of Longwall Powered Support Capacity Using Field Monitored Data of a Longwall Panel and Uncertainty-Based Neural Network. Geotech Geol Eng 34, 2033–2052 (2016). https://doi.org/10.1007/s10706-016-0081-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10706-016-0081-z

Keywords

  • Longwall mining
  • Powered support
  • Leg pressure
  • Bayesian neural network

Search

Navigation