Ebtehaj, I. and Bonakdari, H. and Khoshbin, F. and Hin, Ch. Joo Bong and Ab Ghanid, A. (2017) Development of group method of data handling based on genetic algorithm to predict incipient motion in rigid rectangular storm water channel. Scientia Iranica, 24 (3). pp. 1000-1009. ISSN 1026-3098
|
PDF
- Submitted Version
Available under License Creative Commons Attribution. Download (219kB) | Preview |
Abstract
Sediment transport is a prevalent vital process in uvial and coastalenvironments, and \incipient motion" is an issue inseparably bound to this topic. Thisstudy utilizes a novel hybrid method based on Group Method of Data Handling (GMDH)and Genetic Algorithm (GA) to design GMDH structural (GMDH-GA). Also, SingularValue Decomposition (SVD) was utilized to compute the linear coefficient vectors. Inorder to predict the densimetric Froude number (Fr), the ratio of median diameter ofparticle size to hydraulic radius (d=R) and the ratio of sediment deposit thickness tohydraulic radius (ts=R) are utilized as e ective parameters. Using three di erent sources ofexperimental data and GMDH-GA model, a new equation is proposed to predict incipientmotion. The performance of development equation is compared using GMDH-GA andtraditional equations . The results indicate that the presented equation is more accurate(RMSE= 0:18 andMAPE= 6:48%) than traditional methods. Also, a sensitivityanalysis is presented to study the performance of each input combination in predictingincipient motion (15) Development of Group Method of Data Handling based on Genetic Algorithm to predict incipient motion in rigid rectangular storm water channel.
Item Type: | Article |
---|---|
Subjects: | T Technology > TD Environmental technology. Sanitary engineering > TD429.5-480.7 Water purification. Water treatment and conditioning. Saline water conversion |
Divisions: | Kampus Kejuruteraan (Engineering Campus) > Pusat Penyelidikan Kejuruteraan Sungai dan Saliran Bandar (REDAC) > Article |
Depositing User: | Administrator Automasi |
Date Deposited: | 08 Dec 2017 02:12 |
Last Modified: | 08 Dec 2017 02:15 |
URI: | http://eprints.usm.my/id/eprint/37853 |
Actions (login required)
View Item |