Application of Artificial Intelligence for Prediction of Swelling Potential of Clay-Rich Soils
- PDF / 2,592,952 Bytes
- 17 Pages / 547.087 x 737.008 pts Page_size
- 99 Downloads / 172 Views
(0123456789().,-volV) ( 01234567 89().,-volV)
ORIGINAL PAPER
Application of Artificial Intelligence for Prediction of Swelling Potential of Clay-Rich Soils Birhanu Ermias . Vikram Vishal
Received: 9 November 2018 / Accepted: 13 June 2020 Springer Nature Switzerland AG 2020
Abstract Susceptibility of fine grained soils to swelling and shrinkage problems is crucial for safe design of infrastructure, construction and maintenance. However, quantification of soil response and measurement of their geotechnical properties is time taking, expensive and involves destructive tests. Therefore, dependable forecasting models are necessary that calculate swell percentage from results of quick, inexpensive and non-destructive tests. In this paper, a three-layer feedforward neural network (ANN-TFN) was applied in order to envisage swell percentage of fine grained soils and the results were compared with that of multiple regression (MR). The parameters considered as input were activity, clay, liquid limit, plastic limit, plasticity index and fines while swell percentage was used as output. The best ANN-TFN model demonstrated root mean square errors (RMSE) of 1.529, sum of squares errors (SSE) of 369.3, and coefficient of correlation (R2) of 0.80. MR model displayed 1.756 (RMSE), 487.2 (SSE), and 0.508 (R2). The maximum R2 values obtained by simple regression was 0.5. Overall, the established three-layer feedforward neural network models B. Ermias V. Vishal (&) Department of Earth Sciences, Indian Institute of Technology Bombay, Mumbai, India e-mail: [email protected] B. Ermias Department of Geology, Salale University, P.O. Box 245, Fitche, Ethiopia
(ANN-TFN 1-6) showed significantly higher prediction performances than either multiple regression or simple regression models. Moreover, the use of Levenberg–Marquardt as training parameter and tan sigmoid as transfer function were noted to be more appropriate for good prediction performance in this problem. Hence, the result of the present study concludes that practice of the ANN-TFN model to determine swell percentage of fine grained soil is a promising approach for increasing the confidence of making accurate decisions during the soil engineering works. Keywords Three-layer feedforward network ANN Levenberg–marquardt Multiple regression Fine grained soil Tan-sigmoid
1 Introduction The engineering performances of fine grained soils used as foundation substances are considerably affected by the geologic and climatic regime of the area, the total water content and the energy binding the soil. The most crucial geotechnical challenge of finegrained soil is identifying and evaluating its vulnerability to contraction and expansion problems; as different soils swell and shrink at different rates based on the amount of expansive minerals present in it. For instance, clayey materials expand and contract at a
123
Geotech Geol Eng
considerable degree whereas sand and gravel shrink slightly. Therefore, unless determined and considered well, swelling problems of soil ma
Data Loading...
