A Radial Basis Function Neural Network Approach for Compressive Strength Prediction of Stabilized Soil

This study considers the use of artificial neural networks (ANNs) to predict the unconfined compressive strength (UCS) of soil-stabilizer mix. Radial basis function (RBF) as one of the most widely used ANN architectures is utilized to construct comprehensive models to relate the UCS of stabilized soil to the properties of natural soil and type and quantity of stabilizing additives. A comprehensive set of data obtained from previously published stabilization test results was used for model development. A subsequent parametric study was carried out and the trends of the results have been confirmed via previous laboratory studies. The RBF based estimates are compared with the experimental and numerical results of other researchers and found to be more accurate.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784410431
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Heshmati, Ali Akbar
  • Alavi, Amir Hossein
  • Keramati, Mohsen
  • Gandomi, Amir Hossein
• Conference:
  • GeoHunan International Conference: Challenges and Recent Advances in Pavement Technologies and Transportation Geotechnics
  • Location: Changsha Hunan, China
  • Date: 2009-8-3 to 2009-8-6
• Publication Date: 2009

Language

• English

Media Info

• Media Type: Print
• Features: Figures; References; Tables;
• Pagination: pp 147-153
• Monograph Title: Road Pavement Material Characterization and Rehabilitation: Selected Papers From the 2009 GeoHunan International Conference

Subject/Index Terms

• TRT Terms: Compressive strength; Forecasting; Mixtures; Neural networks; Soil stabilization
• Subject Areas: Geotechnology; Highways; I42: Soil Mechanics;

Filing Info

• Accession Number: 01139940
• Record Type: Publication
• ISBN: 9780784410431
• Files: TRIS
• Created Date: Sep 18 2009 7:08AM