ABSTRACT
In this paper, two artificial intelligence (AI) techniques, including Deep Learning (DL) and Multi-Layer Perceptron (MLP), have been applied to predict the pressure fluctuations coefficient (CʹP) along the submerged and free jumps at the bottom of the USBR Type II stilling basin, based on the geometric and hydraulic parameters. This coefficient is significant for evaluating the uplift and cavitation phenomena within the stilling basins. The measurements were conducted in a laboratory flume using the pressure transducers and the data acquisition system. The maximum values of CʹP occurred at the beginning of the stilling basin. The DL algorithm contains three hidden layers using (100,100,100) hidden neurons. The optimal structure for the MLP model was found to be 5–10‒1. In the testing set, using the DL model, the values of determination coefficient (R2), root mean square error (RMSE), mean absolute error (MAE), and Legate and McCabe’s Index (LMI) were obtained 0.915, 0.003, 0.002, and 0.743, respectively. For the MLP model, the same values were obtained 0.522, 0.009, 0.007, and 0.199, respectively. It was verified that the DL model gives more accurate results for the CʹP coefficient.
Acknowledgments
The authors would like to give their gratitude to Dr. Mandeep Kaur Saggi, Department of Computer Science, Thapar Institute of Engineering and Technology, Patiala, India, and Prof. Mohammad Ali Ghorbani, Department of Water Engineering, University of Tabriz, Iran, for their assistance in the modeling of AI techniques.
Disclosure Statement
No potential conflict of interest was reported by the authors.
Correction Statement
This article has been republished with minor changes. These changes do not impact the academic content of the article.