شناسایی مکان و دبی پمپاژ چاه‌های ناشناخته با استفاده از الگوریتم اتوماتای یادگیر.

Identification the Location and Pumping Discharge of Unknown Wells Using the Learning Automata Algorithm.

The present article proposes a model using the inverse problem to find locations and pumping discharges of unknown wells. The simulation is performed by using the two-dimensional groundwater flow equation, which is solved by the finite difference numerical technique. The learning automata algorithm has been used as a tool for optimization. The simulation and the optimization models are linked to obtaining the final model. To identify the location and discharge of the unknown wells, the proposed model changes the discharges of the wells and studies the influence on the objective function which is the root mean square error of the calculated and observed piezometric head. The wells which increase the objective function are deleted. After the completion of this stage, the locations of the wells are moved to the vicinity in all directions and the locations which yield fewer errors in terms of the objective function will result in the final locations. To check the efficiency of this model, two hypothetical aquifers were used in a steady and unsteady flow state, in which there are some unknown wells. The prepared model showed the ability to determine these wells' number, location, and flow rate with the accuracy of the root mean square error of 0.061 meters in the first numerical example and 0.010 in the second numerical example. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Water & Irrigation Management is the property of University of Tehran and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)