Complex CBR (of BC Soil-RHA-Cement Mix) Estimation: Made Easy by ANN Approach [a Soft Computing Technique]
In past days many researchers have been worked on the expansive soil to determine the California Bearing Ratio (CBR) values in a conventional ways, which are time consuming and require lot of manual involvements. So we the authors of this research paper attempted to develop a soft computing technique to prognosticate CBR value by using Artificial Neural Network (ANN), a data driven technique. ANN is a mathematical model inspired from the human brain’s information-processing characteristics, including the parallel processing ability. Over the last few years, the use of ANN has increased in many areas of engineering. In particular have been applied to many geotechnical engineering problems and have demonstrated some degree of success. A review of the literature reveals that ANN has been used successfully in the pile capacity prediction, site characterization and so on. In the present study the Black Cotton (BC) soil has been stabilized by using Rice Husk Ash (RHA) and cement, several experiments have been conducted for different mix combinations under soaked condition. From the obtained results, it is observed that the CBR value of BC soil increases with the addition of RHA and cement combination. The soaked CBR value found to be maximum for the mix of BC soil + 15% RHA + 12% cement. The present study deals with collection of input data base from experimental results, ANN’s training and its testing are adopted to fix the appropriate weighted matrix (Illustrated in Fig (1)) which in turn Prognosticates the CBR value. Experimental results have been compared with the CBR values prognosticated by using ANN and comparison graphs also plotted (Illustrated in fig (4)). The results of this study will contribute for the prognostication of CBR, which will assist a geotechnical engineer in estimation of CBR, with minimum effort.
A.N. Ramakrishna et al., "Complex CBR (of BC Soil-RHA-Cement Mix) Estimation: Made Easy by ANN Approach [a Soft Computing Technique]", Advanced Materials Research, Vols. 261-263, pp. 675-679, 2011