Abstract
Stresses and deformations in concrete and masonry structures can be significantly altered by creep. Thus, neglecting creep could result in un-conservative design of new structures and/or underestimation of the level of its effect on stress redistribution in existing structures. Brickwork has substantial creep strain that is difficult to predict because of its dependence on many uncontrolled variables. Reliable and accurate prediction models for the long-term, time-dependent creep deformation of brickwork structures are needed. Artificial intelligence techniques are suitable for such applications. A model based on radial basis function neural networks (RBFNN) is proposed for predicting creep and is compared to a multi-layer perceptron neural network (MLPNN) model recently developed for the same purpose. Accurate prediction of creep was achieved due to the simple architecture and fast training procedure of RBFNN model especially when compared to MLPNN model. The RBFNN model shows good agreement with experimental creep data from brickwork assemblages collected over the last 15 years.







Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Abbreviations
- AI:
-
Artificial intelligence
- ANN:
-
Artificial neural networks
- BiasJack(PE J ):
-
Jackknife bias for the prediction error of the creep compliance
- d :
-
Distance from the center of the radial basis function (a measure of the Gaussian curve spread)
- E(t0):
-
Material modulus of elasticity at time of load application t 0
- J(t, t0):
-
Creep compliance between time t 0 and t
- N :
-
Number of basis functions
- n :
-
Total number of observations in the compliance matrix
- PE J :
-
Prediction error in creep compliance
- \( {\text{PE}}_{J}^{ - i} \) :
-
Prediction error calculated for the Jackknife reduced compliance matrix
- J x :
-
Experimentally determined creep compliance
- J p :
-
Predicted creep compliance
- RH:
-
Relative humidity
- RBFNN:
-
Radial basis function neural networks
- SEJack(PE J ):
-
Jackknife standard error for the prediction error of the creep compliance
- t :
-
Time of creep prediction
- t 0 :
-
Time of load application
- W 0 :
-
Bias parameter
- W j :
-
Weight vectors at the output layer of the RBFNN
- x :
-
Input parameter of the radial basis function
- Y (x):
-
Output parameter of the radial basis function
- \( \varepsilon_{\text{cr}} (t,t_{0} ) \) :
-
Creep strain between time t 0 and t
- ε(t 0):
-
Instantaneous strain at time t 0
- φ :
-
Radial basis function
- ϕ(t, t0):
-
Creep coefficient between time t 0 and t
- λ(t0):
-
A constant for creep prediction using modified Maxwell model
- μ :
-
Center of the Gaussian function
- σ :
-
Sustained stress
References
Ameny P, Jessop EL, Loov RE (1980) Strength, elastic and creep properties of concrete masonry. Int J Mason Constr 1(1):33–39
Anand SC, Rahman MA (1991) Numerical modeling of creep in composite masonry walls. J Struct Eng ASCE 117(7):2149–2165
Anzani A, Binda L, Mirabella Roberti G (2000) The effect of heavy persistent actions into the behaviour of ancient masonry. Mater Struct 33:251–261
Anzani A, Garavaglia E, Binda L (2009) Long-term damage of historic masonry: a probabilistic model. Construct Build Mater 23:713–724
Bazant ZP, Ferreti D (2001) Asymptotic temporal and spatial of coupled creep, aging, diffusion and fracture process In: Ulm FJ, Bazant ZP, Wittmann FH (eds) Proceedings of creep, shrinkage and durability mechanics of concrete and other quasi-brittle materials, El-Sevier Science Ltd., pp 121–145
Binda L, Gatti G, Mangano G, Poggi C, Sacchi Landriani G (1992) The collapse of the civic tower of Pavia: a survey of the materials and structure. Mason Int 6(1):11–20
Bishop CM (1996) Neural networks for pattern recognition, 1st edn. Oxford University Press, UK
Brooks JJ, Neville AM (1978) Predicting long-term creep and shrinkage from short-term tests. Mag Concr Res 30(103):51–61
Carpenter W, Barthelemy JF (1994) Common misconceptions about neural networks as approximators. ASCE J Comp Civil Eng 8(3):345–358
Demuth H, Beale M (2001) Neural network toolbox for use with MATLAB®. The Mathworks Inc., MA
Duda RI, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, NY
Efe MO, Kaynak O, Wilamowski BM, Yu X (2001) Radial basis function neural networks in variable structure control of a class of biochemical processes. In: Proceedings of the 27th annual conference of the IEEE industrial electronics society (IECON’ 01), pp 13–18
Efron B, Tibshirani RJ (1993) An introduction to the bootstrap. Chapman and Hall, London
Gardner J, Lockman MJ (2001) Design provisions for drying shrinkage and creep of normal strength concrete. ACI Mater J 98(2):159–167
Gardner NJ, Zhao JW (1993) Creep and shrinkage revisited. ACI Mater J 90(3):236–246
Girosi F, Poggio T (1990) Networks and the best approximation property. Biol Cybern 63:169–176
Ham FM, Kostanic I (2001) Principles of neurocomputing for science and engineering. McGraw-Hill, Singapore
Hamilton HR III, Badger CCR (2000) Creep losses in post-tensioned concrete masonry. TMS J 18:1
Hannant DJ (1968) The mechanism of creep in concrete. Mater Struct 1(5):403–410
Hartman EJ, Keeler JD, Kowalski JM (1990) Layered neural networks with Gaussian hidden units as universal approximations. Neural Comput 2(2):210–215
Harvey RJ, Hughes TG (1995) On the representation of masonry creep by rheological analogy. In: Proceedings of the ASCE structural congress 1, pp 385–396
Harvey RJ, Lenczner D (1993) Creep prestress losses in concrete masonry. In: Proceedings of 5th RILEM international symposium on creep and shrinkage in concrete, Barcelona, Spain, pp 71–76
Hilsdorf HK, Müller HS (1979) Comparison of methods to predict time-dependent strains of concrete. Institute für Baustofftechnologie, Universität Karlsruhe (TH), Germany, p 91
Hjorth JSU (1994) Computer intensive statistical methods: validation model selection and bootstrap. Chapman and Hall, London
Lenczner D (1969) Creep in model brickwork. In: Johnston FB (ed) Proceedings of designing engineering and construction with masonry products, Houston, Texas, USA (1958–1969)
Lenczner D (1986) Creep and prestress losses in brick masonry. Struct Eng 64B(3):57–62
López C, Carol I, Murcia J (2001) Mesostructural modeling of basic creep at various stress levels. In: Ulm FJ, Bazant ZP, Wittmann FH (eds) Proceedings creep, shrinkage and durability mechanics of concrete and other quasi-brittle materials, El-Sevier Science Ltd., pp 101–106
Martinez WL, Martinez AR (2002) Computational statistics handbook with MATLAB®. Chapman & Hall/CRC Press, NY
Masonry Design for buildings (limit states design)—structures (design) (1994) CSA-S304.1-94. Ontario, Canada
Masonry in Buildings. Revisions of Australian standards-SAA (1995) SAA-AS 3700/1988. Standards Association of Australia, Sydney
Model code for concrete structures (1993) CEP-FIP model code 90. Comité Euro-International du Beton (CEB)—Fédération Internationale de la Précontrainte (FIP), Thomas Telford Ltd, London
Moody J, Darken CJ (1989) Fast learning in networks of locally tuned processing units. Neural Comput 1(2):281–294
Morgan DR (1974) Possible mechanisms of influence of admixtures on drying shrinkage and creep in cement paste and concrete. Mater Struct 7(40):283–309
Neville AM, Dilger WH, Brooks JJ (1983) Creep of plain and structural concrete, 1st edn. Construction Press, London
Reda Taha MM, Noureldin A, El-Sheimy N, Shrive NG (2003) Artificial neural network for predicting creep with an example application to structural masonry. Can J Civil Eng 30:523–532
Sayed-Ahmed E, Shrive NG, Tilleman D (1998) Creep deformations of clay masonry structures: a parametric study. Can J Civil Eng 25(1):67–80
Schultz AE, Scolforo M (1992) Engineering design provisions for prestressed masonry, part 2—steel stresses and other considerations. TMS J 10:2
Shao J, Tu D (1995) The jackknife and bootstrap. Springer, NY
Shrive NG, England GL (1981) Effect of time dependent movements in composite and post-tensioned masonry. Int J Mason Constr 1(3):25–29
Shrive NG, Reda Taha MM (2003) Effects of creep on new masonry structures. In: Proceedings of the eighth international conference on structural studies, repairs and maintenance of heritage architecture, Halkidiki, Greece
Taneja R, Shrive NG, Huizer A (1986) Loss of prestress in post-tensioned hollow masonry walls. In: Proceedings of ASCE, advances in analysis of masonry structures, pp 76–93
Tsoukalas LH, Uhrig RE (1997) Fuzzy and neural approaches in engineering, 1st edn. Wiley, NY
Van Zijl GPAG (1999) A Numerical formulation for masonry creep, shrinkage and cracking. Series 11—engineering mechanisms 01. Delft University Press, The Netherlands
Warren D, Lenczner D (1982) Measurement of the creep strain distribution in an axially loaded brickwork wall. In: Proceedings of the second North American masonry conference
Acknowledgments
This research is supported by (1) research grant to the third author from the Natural Science and Engineering Research Council (NSERC) of Canada, (2) The research grant for the first author from Smart Engineering Research Group, University Kebangsaan Malaysia. Special thanks to Mr. Dan Tilleman from the University of Calgary for performing the experimental tests for brickwork creep testing.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
El-Shafie, A., Abdelazim, T. & Noureldin, A. Neural network modeling of time-dependent creep deformations in masonry structures. Neural Comput & Applic 19, 583–594 (2010). https://doi.org/10.1007/s00521-009-0318-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-009-0318-3