The use of artificial neural networks to predict the effect of sulphate attack on the strength of cemented paste backfill

The growing use of cemented paste backfill (CPB) as a ground support method in mining and also as an environmentally friendly alternative for mine waste disposal demands a better understanding of the different processes that affect its strength. Due to its nature as cement based material, CPB is prone to the progressive loss of strength with sulphate attacks under certain conditions. The paper provides a background to sulphate attacks in CPB and artificial neural networks (ANN) and presents a model to predict the unconfined compressive strength of a CPB under sulphate attack, based on different water cement ratios, binder composition and binder content.RésuméL’usage croissant de remblais cimentés (CPB), comme méthode de soutènement des terrains en travaux miniers et aussi comme technique alternative respectueuse de l’environnement pour les stockages de stériles miniers, exige une meilleure compréhension des différents processus qui affectent leur résistance. Du fait de leur nature de matériau à base de ciment, les CPB sont sujets à une perte progressive de résistance du fait des attaques sulfatées sous certaines conditions. L’article fait le point sur les attaques sulfatées affectant les CPB et sur les réseaux de neurones (ANN) et présente un modèle pour prévoir la résistance à la compression simple d’un CPB sous attaque sulfatée, considérant différentes formulations eau-ciment, la composition du liant et la teneur en liant.

[1]  Mauro Serra,et al.  Concrete strength prediction by means of neural network , 1997 .

[2]  Timothy Masters,et al.  Probabilistic Neural Networks , 1993 .

[3]  Ayhan Kesimal,et al.  Effect of properties of tailings and binder on the short-and long-term strength and stability of cemented paste backfill , 2005 .

[4]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[5]  S. Servant,et al.  In-situ mechanical characterization of a paste backfill with a self-boring pressuremeter , 2000 .

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[8]  Mamadou Fall,et al.  Modeling the effect of sulphate on strength development of paste backfill and binder mixture optimization , 2005 .

[9]  A. Neville.  Properties of Concrete , 1968 .

[10]  Mamadou Fall,et al.  Mechanical response of a mine composite material to extreme heat , 2008 .

[11]  Mamadou Fall,et al.  Experimental characterization of the influence of tailings fineness and density on the quality of cemented paste backfill , 2005 .

[12]  E. Samson,et al.  Durability of concrete — Degradation phenomena involving detrimental chemical reactions , 2008 .

[13]  Maria Q. Feng,et al.  Application of neural networks for estimation of concrete strength , 2002 .

[14]  P. Brown,et al.  Thaumasite formation and other forms of sulfate attack , 2002 .

[15]  Leah L. Rogers,et al.  Solving Problems in Environmental Engineering and Geosciences with Artificial Neural Networks , 1996 .

[16]  F. W. Brackebusch,et al.  Basics of paste backfill systems , 1995 .

[17]  Tikou Belem,et al.  A contribution to understanding the hardening process of cemented pastefill , 2004 .

[18]  Barry J. Wythoff,et al.  Backpropagation neural networks , 1993 .

[19]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[20]  Bryant Mather,et al.  Sulfate Attack on Concrete: Research Needs , 1991 .

[21]  L. M. Amaratunga,et al.  Development of a high modulus paste fill using fine gold mill tailings , 1997 .

[22]  Nagaratnam Sivakugan,et al.  Underground Mining with Backfills , 2007, Soils and Rocks.

[23]  Yves Chauvin,et al.  Backpropagation: the basic theory , 1995 .

[24]  David V. Boger,et al.  Environmental rheology for waste minimisation in the minerals industry , 2002 .

[25]  Mamadou Fall,et al.  Mix proportioning of underground cemented tailings backfill , 2008 .

[26]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[27]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[28]  P. K. Mehta.  Concrete: Structure, Properties, and Materials , 1992 .

[29]  Wolfgang Czernin,et al.  Cement chemistry and physics for civil engineers , 1962 .

[30]  Moisés Frı´as,et al.  Effect of incorporating ferroalloy industry wastes as complementary cementing materials on the properties of blended cement matrices , 2008 .

[31]  Tao Ji,et al.  A concrete mix proportion design algorithm based on artificial neural networks , 2006 .

[32]  D. Nordstrom,et al.  Initiation of aqueous pyrite oxidation by dissolved oxygen and by ferric iron , 1987 .

[33]  Mamadou Fall,et al.  WITHDRAWN: Influence of curing temperature on strength, deformation behaviour and pore structure of cemented paste backfill at early ages , 2006 .

[34]  Ivars Neretnieks,et al.  Long-term environmental impact of tailings deposits , 2006 .

[35]  A. Neville.  THE CONFUSED WORLD OF SULFATE ATTACK ON CONCRETE , 2004 .

[36]  M. A. Bhatti,et al.  Predicting the compressive strength and slump of high strength concrete using neural network , 2006 .

[37]  Henry Jean Claude Celestin.  Geotechnical properties of cemented paste backfill and tailings liners: Effect of mix components and temperature , 2009 .

[38]  Mukesh Pokharel.  Geotechnical and environmental responses of paste tailings systems to coupled thermo-chemical loadings , 2008 .

[39]  M. Collepardi,et al.  A state-of-the-art review on delayed ettringite attack on concrete , 2003 .

[40]  Bing Tian,et al.  Does gypsum formation during sulfate attack on concrete lead to expansion , 2000 .

[41]  Jan Skalny,et al.  Materials science of concrete , 1989 .

[42]  A. Burak Göktepe,et al.  Image analysis of sulfate attack on hardened cement paste , 2008 .

[43]  M. Fall,et al.  Modeling the heat development in hydrating CPB structures , 2009 .

[44]  Ata Akcil,et al.  Destruction of cyanide in gold mill effluents: biological versus chemical treatments. , 2003, Biotechnology advances.

[45]  Xu Zhongzi,et al.  The process of sulfate attack on cement mortars , 1996 .

[46]  Angel Irabien,et al.  Neural network prediction of unconfined compressive strength of coal fly ash–cement mixtures , 2003 .

[47]  A. K. Rigler,et al.  Accelerating the convergence of the back-propagation method , 1988, Biological Cybernetics.