A practical hybrid NNGA system for predicting the compressive strength of concrete containing natural pozzolan using an evolutionary structure
Source abstract
Abstract
Abstract Many researchers are interested in predicting the concrete compressive strength, resulting in quite a few linear and nonlinear regression equations. Alternatively, other models have been developed to produce more sophisticated systems by applying soft computing techniques, the majority of which have rarely been used beyond classic problems, such as function optimization or approximation by genetic algorithms (GAs), or neural networks (NNs). Our study proposes an evolutionary structure with a more complex NN in order to achieve the full potential of these techniques, which the genetics of neural systems promises to do. It consists of integrating a GA to optimize the connection weights for each neuron of an NN developed previously. The idea behind this combination is to develop an NNGA model prediction of the compressive strength of concrete containing natural pozzolan. Model learning and testing were first performed based on the back-propagation algorithm. Then, the model was optimized using the proposed evolutionary structure based upon GA. More than 400 experimental data collected from past studies were used in building this model. The hybrid NNGA model was compared with NN model using the same architecture, show that the NNGA is more performant and better than NN alone. The proposed hybrid model was also experimentally validated, very acceptable results with a high correlation coefficient R2 equal to 0.93, yielding comparable results to those obtained by the ACI 209-08 and CEB-FIP models with R2 values equal to 0.95 and 0.96, respectively. However, it can help to predict the compressive strength of a specified concrete mix at any age without knowing in prior the 28 days’ compressive strength of this given concrete as it is the case in ACI 208-09 and CEB-FIB Codes. The main feature of this system is its flexibility to reduce significantly the scale of the experiment using a system graphical user interface.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Innovative concrete reinforcement materials · Concrete Corrosion and Durability · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (65)
Show source-provided references
1. Le logiciel BétonlabPro 3
2. Bullard · 2009 · vol. 266 · 27
3. Computer-aided design for optimum concrete mixtures10.1016/j.cemconcomp.2006.11.001 ↗
4. Statistical modelling and prediction of compressive strength of concrete
5. Prediction of compressive strength of concrete from early age test result using design of experiments (RSM)
6. Steam curing of concrete10.1680/macr.1949.1.2.79 ↗
7. Prévision de la résistance à la compression au jeune age du béton: application de la méthode du temps équivalent
8. Sur la compacité des matériaux hydrauliques
9. Abrams · 1918 · 1
10. ACI Committee 209.2R-08 · 2008
11. Model Code 2010, The fib Model Code for Concrete Structures 2010, Comité Euro-International du Beton. fib Bulletin N 65, 2012, 350p.
12. Fly ash concrete mix design and water–cement ratio law
13. Efficiency of fly ash in concrete with age10.1016/0008-8846(96)00011-7 ↗
14. Dreyfus · 2002
15. Zadeh · 1996
16. Holland · 1992
17. Application of new information technology on concrete: an overview10.3846/13923730.2011.574343 ↗
18. A concrete mix proportion design algorithm based on artificial neural networks10.1016/j.cemconres.2006.01.009 ↗
19. Modeling of hydration reactions using neural networks to predict the average properties of cement paste10.1016/j.cemconres.2004.08.004 ↗
20. Exploring concrete slump model using artificial neural networks10.1061/(ASCE)0887-3801(2006)20:3(217) ↗
21. Neural networks for predicting properties of concretes with admixtures10.1016/S0950-0618(01)00006-X ↗
22. A system for predicting concrete properties using neural networks (NN) with principal component analysis (PCA) Technique10.12989/cac.2012.10.6.557 ↗
23. Estimation of sulfate expansion level of PC mortar using statistical and neural approaches10.1016/j.conbuildmat.2005.01.041 ↗
24. Neural network prediction of concrete degradation by sulphuric acid attack10.1080/15732470500253065 ↗
25. Cement roller mill control by fuzzy logic controller
26. Fuzzy logic model for the prediction of cement compressive strength10.1016/j.cemconres.2004.01.020 ↗
27. A new approach to determination of compressive strength of fly ash concrete using fuzzy logic
28. Empirical modeling of splitting tensile strength from cylinder compressive strength of concrete by genetic programming
29. Prediction of compressive strength of concrete using artificial neural network and genetic programming10.1155/2016/7648467 ↗
30. Prediction of the mechanical properties of structural recycled concrete using multivariable regression and genetic programming10.1016/j.conbuildmat.2015.12.136 ↗
31. Empirical modeling of fresh and hardened properties of self-compacting concretes by genetic programming10.1016/j.conbuildmat.2007.04.021 ↗
32. Genetic programming based formulation for fresh and hardened properties of self-compacting concrete containing pulverised fuel ash10.1016/j.conbuildmat.2009.02.012 ↗
33. Modeling slump of ready mix concrete using genetic algorithms assisted training of artificial neural networks10.1016/j.eswa.2014.08.048 ↗
34. Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic10.1016/j.commatsci.2007.04.009 ↗
35. Prediction of concrete compressive strength: Research on hybrid models genetic based algorithms and ANFIS10.1016/j.advengsoft.2013.09.004 ↗
36. Mosaic copy number variation in human neurons10.1126/science.1243472 ↗
37. 2014
38. DELPHI 10 · 2014 · 1106
39. Goldberg · 1989
40. Holland · 1992
41. Genetic algorithm optimization problems
42. Gen · 1999
43. A hybrid genetic algorithm for reinforced concrete flat slab buildings10.1016/j.compstruc.2004.10.013 ↗
44. Modeling shear capacity of RC slender beams without stirrups using genetic algorithms10.12989/sss.2007.3.1.051 ↗
45. Genetic algorithm in mix proportioning of high-performance concrete10.1016/j.cemconres.2003.08.018 ↗
46. Optimization of the weights and asymmetric activation function family of neural network for time series forecasting10.1016/j.eswa.2013.05.053 ↗
47. Prediction of concrete strength using neural-expert system10.1061/(ASCE)0899-1561(2006)18:3(462) ↗
48. Haykin · 1994
49. Galushkin · 2007
50. Chauvin · 1995
51. Ramezanianpour · 1992 · 209
52. Properties of pastes, mortars and concretes containing natural pozzolan10.1016/0008-8846(95)00053-F ↗
53. Dhir · 2006
54. Effect of large amounts of natural pozzolan addition on properties of blended cements10.1016/j.cemconres.2004.07.022 ↗
55. Optimum usage of a natural pozzolan for the maximum compressive strength of concrete10.1016/j.cemconres.2004.02.008 ↗
56. Properties of concrete containing diatomaceous earth
57. Development of volcanic ash concrete: strength, durability, and microstructural investigations
58. High-volume natural pozzolan concrete for structural applications
59. Performance of Pakistani volcanic ashes in mortars and concrete10.1139/L08-093 ↗
60. Durability of concrete containing a natural pozzolan as defined by a performance-based approach10.1016/j.conbuildmat.2009.08.002 ↗
61. Compressive strength of volcanic ash/ordinary portland cement laterized concrete
62. Effect of specimen sizes, specimen shapes, and placement directions on compressive strength of concrete10.1016/j.nucengdes.2005.08.004 ↗
63. Selecting the most efficient genetic algorithm sets in solving building optimization problem10.1016/j.ijsbe.2014.07.003 ↗
64. Neville · 1995
65. Mehta · 2005