Development of Genetic Algorithm based Neural Network Model for Predicting Workability and Strength of High Performance Concrete
Vaishali G. Gorphade1, H. Sudarsana Rao2, M. Beulah3

1Dr. Vaishali G.Gorphade, Associate professor , Department of Civil Engineering, JNTUCEA, Anantapur , Andhra Pradesh, India.
2Dr. H. Sudarsana Rao, Rector, JNTU, Anantapur, Andhra Pradesh, India.
3M. Beulah, Department of Civil Engineering, Assistant Professor, Christ University, Bangalore-Karnataka, India.
Manuscript received on May 05, 2014. | Revised Manuscript Received on May 18, 2014. | Manuscript published on May 20, 2014. | PP: 1-9 | Volume-2, Issue-6, May 2014. | Retrieval Number: F0469052614/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering & Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: This paper presents an results of experimental investigation conducted to evaluate the possibilities of adopting Genetic Algorithm (GA) based Artificial Neural Networks (ANN) to predict the workability and strength characteristics of High Performance Concrete (HPC) with different water-binder ratios (0.3, 0.325, 0.35, 0.375, 0.4, 0.425, 0.45, 0.475 & 0.5) and different aggregate binder ratios (2, 2.5 & 3) and different percentage replacement of cement by mineral admixtures such as Flyash, Metakaolin and Silicafume (0, 10, 20 & 30%) as input vectors. The network has been trained with experimental data obtained from laboratory experimentation. The Artificial Neural Network learned the relationship for predicting the Compaction factor, Vee-bee time, Compressive of HPC in 1300 training epochs. The Artificial Neural Network learned the relationship for predicting the Compressive strength, Tensile strength, Flexural strength and Young’s Modulus of HPC in 2000 training epochs. After successful learning the GA based ANN models predicted the workability and strength characteristics satisfying all the constraints with an accuracy of about 95%. The various stages involved in the development of genetic algorithm based neural network models are addressed at length in this paper.
Keywords: Artificial Neural Network (ANN), Back Propagation (BP), Genetic Algorithm (GA), Mineral Admixtures (MA), Root Mean Square Error (RMSE). Workability characteristics and Strength Characteristics (SC).