Developing empirical formulae for scour depth in front of inclined bridge piers

dc.contributor.author Fedakar, Halil İbrahim
dc.contributor.author Dincer, Ali Ersin
dc.contributor.author Bozkuş, Zafer
dc.contributor.authorID 0000-0002-7561-5363 en_US
dc.contributor.authorID 0000-0002-4662-894X en_US
dc.contributor.department AGÜ, Mühendislik Fakültesi, İnşaat Mühendisliği Bölümü en_US
dc.contributor.institutionauthor Fedakar, Halil İbrahim
dc.contributor.institutionauthor Dincer, Ali Ersin
dc.date.accessioned 2024-04-19T07:59:54Z
dc.date.available 2024-04-19T07:59:54Z
dc.date.issued 2023 en_US
dc.description.abstract Because of the complex flow mechanism around inclined bridge piers, previous studies have proposed different empirical correlations to predict the scouring depth in front of piers, which include regression analysis developed from laboratory measurements. However, because these correlations were developed for particular datasets, a general equation is still required to accurately predict the scour depth in front of inclined bridge piers. The aim of this study is to develop a general equation to predict the local scour depth in front of inclined bridge pier systems using multilayer perceptron (MLP) and radial-basis neural-network (RBNN) techniques. The experimental datasets used in this study were obtained from previous research. The equation for the scour depth of the front pier was developed using five variables. The results of the artificial neural-network (ANN) analyses revealed that the RBNN and MLP models provided more accurate predictions than the previous empirical correlations for the output variables. Accordingly, analytical equations derived from the RBNN and MLP models were proposed to accurately predict the scouring depth in front of inclined bridge piers. Moreover, from the sensitivity analyses results, we determined that the scour depths in front of the front and back piers were primarily influenced by the inclination angle and flow intensity, respectively. en_US
dc.description.abstract Neka istraživanja predlažu različite empirijske korelacije kako bi se predvidjela dubina podlokavanja ispred nagnutih stupova mosta kroz regresijsku analizu dobivenu laboratorijskim mjerenjima zbog složenih mehanizama toka oko nagnutih stupova mosta. Međutim, kako su se te korelacije razvile za određeni skup podataka, opća je jednadžba i dalje potrebna da bi se točno predvidjela dubina podlokavanja ispred nagnutih stupova mosta. Glavni je cilj istraživanja razviti opću jednadžbu kako bi se predvidjela dubina podlokavanja ispred nagnutih stupova mosta kroz višeslojni perceptron (MLP) i tehnike neuronske mreže s radijalnim baznim funkcijama (RBNN). Eksperimentalni skupovi podataka koji se primjenjuju u ovom istraživanju skupljeni su se iz prijašnjih istraživanja. Jednadžba za dubinu podlokavanja prednjeg stupa koristi se primjenom pet varijabl. Rezultati analiza umjetne neuronske mreže (ANN) otkrivaju da su modeli RBNN i MLP omogućili preciznija predviđanja nego prethodne empirijske korelacije kad su u pitanju izlazne varijable. Prema tome, predlažu se analitičke jednadžbe dobivene RBNN i MLP modelima za točno predviđanje dubine podlokavanja ispred nagnutih stupova mosta. Štoviše, na temelju rezultata analize osjetljivosti utvrđuje se da je na dubinu podlokavanja ispred prednjih i stražnjih stupova najviše utjecao kut nagiba, odnosno intenzitet toka. en_US
dc.identifier.endpage 256 en_US
dc.identifier.issn 0350-2465
dc.identifier.issue 3 en_US
dc.identifier.startpage 239 en_US
dc.identifier.uri https://doi.org/10.14256/JCE.3507.2022
dc.identifier.uri https://hdl.handle.net/20.500.12573/2106
dc.identifier.volume 75 en_US
dc.language.iso eng en_US
dc.publisher Croatian Association of Civil Engineers en_US
dc.relation.isversionof 10.14256/JCE.3507.2022 en_US
dc.relation.journal Gradjevinar en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.subject pier scour en_US
dc.subject artificial neural network en_US
dc.subject inclination angle en_US
dc.subject bridge piers en_US
dc.subject multilayer perceptron en_US
dc.subject radial-basis neural network en_US
dc.subject podlokavanje stupa en_US
dc.subject umjetna neuronska mreža en_US
dc.subject kut nagiba stupova mosta en_US
dc.subject višeslojni perceptron en_US
dc.subject radijalna bazna neuronska mreža en_US
dc.title Developing empirical formulae for scour depth in front of inclined bridge piers en_US
dc.title.alternative Razvijanje empirijske jednadžbe za dubinu podlokavanja ispred nagnutih stupova mosta en_US
dc.type article en_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
JCE-75-2023-3-3-3507-EN (1).pdf
Size:
2.78 MB
Format:
Adobe Portable Document Format
Description:
Makale Dosyası

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.44 KB
Format:
Item-specific license agreed upon to submission
Description: