Genetic algorithm based ANN to predict compressive strength of siphon for different fiber volume fraction

  • Authors

    • Gottapu Santosh Kumar
    • K Rajasekhar
    2018-09-22
    https://doi.org/10.14419/ijet.v7i4.5.25057
  • ANN, Genetic Algorithm, Manufactured Sand, MSE, SIFCON.

  • This paper presents the applicability of Genetic Algorithm based Artificial Neural Network (GAANN) for predicting Compressive strength of Slurry Infiltrated Fibrous Concrete (SIFCON) prepared with manufactured sand for different fibre volume fraction (8%, 10% and 12%) as input vector. The network has been trained with data obtained from experimental work. The proposed GAANNs model is successfully used for predicting compressive strength of SIFCON (output vector) for various fibre volume fractions (2%, 4%, 6%, 14%, 16%, 18%, 20% and 22%) at 7 days, 28 days and 56 days of curing respectively. After successful learning GA based ANN model pre- dicted the compressive strength property satisfying all the constrains with an accuracy of about 85%.The various stages involved in the development of genetic algorithm based neural network are addressed in depth in this paper.

     

     

  • References

    1. [1] Parameswaran VS (1990), Studies on Slurry Infiltrated Fibrous Concrete, Transportation Research Record 1382.

      [2] Kuldeep Dagar (2012), Slurry infiltrated fibrous concrete, International Journal of Applied Engineering and Technology 2 ISSN: 2277-212X, 99-100.

      [3] Arun Aniyan Thomas and Jeena Mathews (2014), Strength and Behaviour of SIFCON with Different Types of Fibres, International Journal of Civil Engineering and Technology 5, 25- 30.

      [4] Serio Lai, and Marzouk (1997), Concrete strength prediction by means of Neural Network construction and building materials 11, 93-98.

      [5] Yeh IC (1998), Modeling of strength of high performance concrete using Artificial neural Networks, Journal of cement and concrete 28, 1797-1808.

      [6] Guang NH, Zong WJ (2000), Prediction of compressive strength of concrete by neural networks, Journal of Cement Concrete Composites 16, 287-298.

      [7] Raghunath Reddy T (2001), Development of a macro mechanical Neural Network model for steel fibre reinforced concrete, doctoral discussions, JNTU Hyderabad.

      [8] Sudharsana Rao H, Subba Reddy PV, Vaishali G, Chandrasekhara Reddy T (2012), Development of Genetic Algorithm based hybrid Neural Network model for predicting the flexural strength of Ferrocement elements, International Journal of science and Technology 4, 867-873.

      [9] Kasperkiewics J, Racz J, Dubrawski A (1995), HPC strength prediction using ANN, Journal of Composite Civil Engineering 4, 279-284.

      [10] Lai S, Sera M (1997), Concrete strength prediction by means of neural network, Journal of Construction and Building Materials 11, 93-98.

      [11] Lee SC (2003), Prediction of concrete strength using artificial neural networks, Journal of Engineering Structures 25, 849-857.

      [12] Bai J, Wild S, Ware JA, Sabir BB (2003), using neural networks to predict workability of concrete incorporating metakolin and flyash, Journal of Advanced Engineering Software 34, 663-669.

  • Downloads

  • How to Cite

    Santosh Kumar, G., & Rajasekhar, K. (2018). Genetic algorithm based ANN to predict compressive strength of siphon for different fiber volume fraction. International Journal of Engineering & Technology, 7(4.5), 681-684. https://doi.org/10.14419/ijet.v7i4.5.25057