Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Hybrid Artificial Intelligence Methods for Predicting Air Demand in Dam Bottom Outlet

Version 1 : Received: 5 February 2021 / Approved: 9 February 2021 / Online: 9 February 2021 (12:22:04 CET)

How to cite: Narimani, A.; Moghimi, M.; Mosavi, A. Hybrid Artificial Intelligence Methods for Predicting Air Demand in Dam Bottom Outlet. Preprints 2021, 2021020239 (doi: 10.20944/preprints202102.0239.v1). Narimani, A.; Moghimi, M.; Mosavi, A. Hybrid Artificial Intelligence Methods for Predicting Air Demand in Dam Bottom Outlet. Preprints 2021, 2021020239 (doi: 10.20944/preprints202102.0239.v1).

Abstract

In large infrastructures such as dams, which have a relatively high economic value, ensuring the proper operation of the associated hydraulic facilities in different operating conditions is of utmost importance. To ensure the correct and successful operation of the dam's hydraulic equipment and prevent possible damages, including gates and downstream tunnel, to build laboratory models and perform some tests are essential (the advancement of the smart sensors based on artificial intelligence is essential). One of the causes of damage to dam bottom outlets is cavitation in downstream and between the gates, which can impact on dam facilities, and air aeration can be a solution to improve it. In the present study, six dams in different provinces in Iran has been chosen to evaluate the air entrainment in the downstream tunnel experimentally. Three artificial neural networks (ANN) based machine learning (ML) algorithms are used to model and predict the air aeration in the bottom outlet. The proposed models are trained with genetic algorithms (GA), particle swarm optimization (PSO), i.e., ANN-GA, ANN-PSO, and ANFIS-PSO. Two hydrodynamic variables, namely volume rate and opening percentage of the gate, are used as inputs into all bottom outlet models. The results showed that the most optimal model is ANFIS-PSO to predict the dependent value compared with ANN-GA and ANN-PSO. The importance of the volume rate and opening percentage of the dams' gate parameters is more effective for suitable air aeration.

Subject Areas

Dam; bottom outlet; air aeration; prediction; hybrid machine learning; artificial intelligence

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.