STM Article Repository

Alrowais, Raid and Alwushayh, Bandar and Bashir, Muhammad Tariq and Nasef, Basheer M. and Ghazy, Ahmed and Elkamhawy, Elsayed (2023) Modeling and Analysis of Cutoff Wall Performance Beneath Water Structures by Feed-Forward Neural Network (FFNN). Water, 15 (21). p. 3870. ISSN 2073-4441

[thumbnail of water-15-03870.pdf] Text
water-15-03870.pdf - Published Version

Download (9MB)

Abstract

Cutoff walls are widely used to limit seepage, piping, and the uplift under hydraulic structures. Therefore, this study focused on a numerical investigation of the hydraulic performance of cutoff walls beneath hydraulic structures during both static and dynamic conditions, considering location and inclination angle influences. The results confirmed that placing the cutoff wall at the upstream heel was more effective in reducing uplift pressure compared to other placements during static conditions. The inclination angles for the different placements of the cutoff wall had a significant impact on the total uplift pressure, exit hydraulic gradient, and seepage discharge during both static and dynamic states. The earthquakes had a noticeable effect on uplift pressure, seepage discharge, and exit hydraulic gradient. During static conditions, the inclination angle of 90° was the most effective angle for decreasing seepage discharge, irrespective of the cutoff wall position. During an earthquake, the seepage discharge values were high regardless of the inclination angle. In the case of placing a cutoff wall at the upstream heel, the maximum seepage discharge value occurred at an inclination angle of 45°. This study provided insights into the behavior of cutoff walls under different conditions and can inform the design and construction of such structures for effective seepage control. The experimental feed-forward neural network (FFNN) was also successfully built. According to the following criteria (uplift pressure, seepage, and exit hydraulic gradient), the hydraulic performance of cutoff walls beneath hydraulic structures under static conditions can be examined. The FFNN can make predictions with root mean square errors (RMSE) of 0.0697, 0.0021, and 0.0059, respectively, and R2 values of 1.00, 0.9994, and 0.9997.

Item Type: Article
Subjects: GO for ARCHIVE > Multidisciplinary
Depositing User: Unnamed user with email support@goforarchive.com
Date Deposited: 07 Nov 2023 06:44
Last Modified: 07 Nov 2023 06:44
URI: http://eprints.go4mailburst.com/id/eprint/1669

Actions (login required)

View Item
View Item