Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio of Soils

Journal Title: International Journal of Modern Engineering Research (IJMER) - Year 2015, Vol 5, Issue 1

Abstract

The behaviour of soil at the location of the project and interactions of the earth materials during and after construction has a major influence on the success, economy and safety of the work. Another complexity associated with some geotechnical engineering materials, such as sand and gravel, is the difficulty in obtaining undisturbed samples and time consuming involving skilled technician. Knowledge of California Bearing Ratio (C.B.R) is essential in finding the road thickness. To cope up with the difficulties involved, an attempt has been made to model C.B.R in terms of Fine Fraction, Liquid Limit, Plasticity Index, Maximum Dry density, and Optimum Moisture content. A multi-layer perceptron network with feed forward back propagation is used to model varying the number of hidden layers. For this purposes 50 soils test data was collected from the laboratory test results. Among the test data 30 soils data is used for training and remaining 20 soils for testing using 60-40 distribution. The architectures developed are 5-4-1, 5-5-1, and 5-6-1. Model with 5-6-1 architecture is found to be quite satisfactory in predicting C.B.R of soils. A graph is plotted between the predicted values and observed values of outputs for training and testing process, from the graph it is found that all the points are close to equality line, indicating predicted values are close to observed values.

Authors and Affiliations

Phani Kumar Vaddi , Ch. Manjula , P. Poornima

Keywords

Related Articles

 Design, Simulation and Implementation of Flyback based, True Single Stage, Isolated, Power Factor Corrected AC-DC Converter for Solar Array Simulators

Presently most of the Power Factor correction circuits are based on boost topology. They consist of two  stages, one being the power factor correction (pre-regulator) and later DC-DC conversion stage. This paper pre...

 Design of liquid oxygen storage tank with welded joints & its Safety

 In this paper we design a high pressure liquid oxygen storage tank. Liquid oxygen storage tank is leak proof container design to hold and store liquid oxygen at cryogenic temperature at a pressure substantial...

Effect of Nanoparticles on E-Glass Fiber Epoxy Resin Composites

In the present work fabrication of composite material(E-Glass Fiber Epoxy Resin + NANO CaCO3) was carried out and their tensile properties viz tensile strength, tensile strain(%),young's modulus, energy at maxi...

 Enhancement of Power Quality by UPQC Device in SCIG Wind Fram to Weak Grid Connection

 In the last years, the wind power generation incorporated into standard grids has been increased significantly. This situation forced the revision of grid connection code requirements, to guarantee the reliability...

 Voltage Support and Reactive Power Control in Micro-grid using DG

  Distribution Generators(DGs) are the renewable energy resource which can be connected to the grid. When it is connected to the grid it should be operated with controlled voltage and reactive power control. And in...

Download PDF file
  • EP ID EP116526
  • DOI -
  • Views 152
  • Downloads 0

How To Cite

Phani Kumar Vaddi, Ch. Manjula, P. Poornima (2015). Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio of Soils. International Journal of Modern Engineering Research (IJMER), 5(1), 15-21. https://europub.co.uk./articles/-A-116526