Research output: Contribution to conference › Paper

17Downloads
(Pure)

Abstract

Several approaches have been used for estimation of failure time when dam failure occurs. Generalized Regression Neural Network (GRNN) model has been proposed in this present study as a novel method to estimate the dam failure time. It has also made a comparison of the results of the GRNN models with the results obtained from the existing approaches. Various reservoir and dam characteristics have been used in the development of the GRNN models in order to estimate the dam failure time. To obtain the optimum results from the GRNN models, all models was optimized to smooth factor values. The values were found to range from 0.001 to 0.03. Furthermore, training the network took up 85% of the total data and testing the network took up the 15% of the total data. Three statistical indices were used to assess the results of GRNN models. They were the Root Mean Square Error (RMSE), Mean Relative Error (MRE), and Coefficient of Correlation (R2). The results showed that the value of the MRE could be decreased more than 50% by using the GRNN models as compared to the values of the existing empirical techniques.

title = "Estimation Of Failure Time For Embankment Dams",

abstract = "Several approaches have been used for estimation of failure time when dam failure occurs. Generalized Regression Neural Network (GRNN) model has been proposed in this present study as a novel method to estimate the dam failure time. It has also made a comparison of the results of the GRNN models with the results obtained from the existing approaches. Various reservoir and dam characteristics have been used in the development of the GRNN models in order to estimate the dam failure time. To obtain the optimum results from the GRNN models, all models was optimized to smooth factor values. The values were found to range from 0.001 to 0.03. Furthermore, training the network took up 85{\%} of the total data and testing the network took up the 15{\%} of the total data. Three statistical indices were used to assess the results of GRNN models. They were the Root Mean Square Error (RMSE), Mean Relative Error (MRE), and Coefficient of Correlation (R2). The results showed that the value of the MRE could be decreased more than 50{\%} by using the GRNN models as compared to the values of the existing empirical techniques.",

author = "{Mohd Sidek}, Lariyah and Sammen, {Saad Sh} and Mohammed, {Thamer A.} and GHAZALI, {ABD ALHALIM} and {Abdul Aziz}, AZLAN",

Research output: Contribution to conference › Paper

TY - CONF

T1 - Estimation Of Failure Time For Embankment Dams

AU - Mohd Sidek, Lariyah

AU - Sammen, Saad Sh

AU - Mohammed, Thamer A.

AU - GHAZALI, ABD ALHALIM

AU - Abdul Aziz, AZLAN

PY - 2017/8/14

Y1 - 2017/8/14

N2 - Several approaches have been used for estimation of failure time when dam failure occurs. Generalized Regression Neural Network (GRNN) model has been proposed in this present study as a novel method to estimate the dam failure time. It has also made a comparison of the results of the GRNN models with the results obtained from the existing approaches. Various reservoir and dam characteristics have been used in the development of the GRNN models in order to estimate the dam failure time. To obtain the optimum results from the GRNN models, all models was optimized to smooth factor values. The values were found to range from 0.001 to 0.03. Furthermore, training the network took up 85% of the total data and testing the network took up the 15% of the total data. Three statistical indices were used to assess the results of GRNN models. They were the Root Mean Square Error (RMSE), Mean Relative Error (MRE), and Coefficient of Correlation (R2). The results showed that the value of the MRE could be decreased more than 50% by using the GRNN models as compared to the values of the existing empirical techniques.

AB - Several approaches have been used for estimation of failure time when dam failure occurs. Generalized Regression Neural Network (GRNN) model has been proposed in this present study as a novel method to estimate the dam failure time. It has also made a comparison of the results of the GRNN models with the results obtained from the existing approaches. Various reservoir and dam characteristics have been used in the development of the GRNN models in order to estimate the dam failure time. To obtain the optimum results from the GRNN models, all models was optimized to smooth factor values. The values were found to range from 0.001 to 0.03. Furthermore, training the network took up 85% of the total data and testing the network took up the 15% of the total data. Three statistical indices were used to assess the results of GRNN models. They were the Root Mean Square Error (RMSE), Mean Relative Error (MRE), and Coefficient of Correlation (R2). The results showed that the value of the MRE could be decreased more than 50% by using the GRNN models as compared to the values of the existing empirical techniques.