Integrated emitter local loss prediction using artificial neural networks.

Giuseppe Provenzano, Guillermo Palau-Salvador, Álvaro Royuela, Pau Martí

Risultato della ricerca: Article

18 Citazioni (Scopus)

Abstract

This paper describes an application of artificiai neural networks (ANNs) to the prediction of Iocai Iosses from integrated emitters. First, the optimum input-output combination was determined. Then, the mapping capability of ANNs and regression models was compared. Afterwards, a five-input ANN model, which considers pipe and emitter internai diameter, emitter length, emitter spacing, and pipe discharge, was used to develop a local losses predicting tool which was obtained from different training strategies while taking into account a completely independent test set. Finally, a performance index was evaluated for tbe test emitter models studied. Emitter data with Iow reliability were removed from the processo Performance indexes over 80% were obtained for the remaining test emitters.
Lingua originaleEnglish
pagine (da-a)11-22
Numero di pagine12
RivistaJOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING
Volume136
Stato di pubblicazionePublished - 2010

Fingerprint

emitters (equipment)
Neural Networks (Computer)
artificial neural network
neural networks
Neural networks
prediction
model test
spacing
pipe
Pipe
testing
pipes
loss
index
test
spatial distribution

All Science Journal Classification (ASJC) codes

  • Agricultural and Biological Sciences (miscellaneous)
  • Civil and Structural Engineering
  • Water Science and Technology

Cita questo

Integrated emitter local loss prediction using artificial neural networks. / Provenzano, Giuseppe; Palau-Salvador, Guillermo; Royuela, Álvaro; Martí, Pau.

In: JOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING, Vol. 136, 2010, pag. 11-22.

Risultato della ricerca: Article

Provenzano, Giuseppe ; Palau-Salvador, Guillermo ; Royuela, Álvaro ; Martí, Pau. / Integrated emitter local loss prediction using artificial neural networks. In: JOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING. 2010 ; Vol. 136. pagg. 11-22.
@article{204e5196792c4fa981c634bf9ad57321,
title = "Integrated emitter local loss prediction using artificial neural networks.",
abstract = "This paper describes an application of artificiai neural networks (ANNs) to the prediction of Iocai Iosses from integrated emitters. First, the optimum input-output combination was determined. Then, the mapping capability of ANNs and regression models was compared. Afterwards, a five-input ANN model, which considers pipe and emitter internai diameter, emitter length, emitter spacing, and pipe discharge, was used to develop a local losses predicting tool which was obtained from different training strategies while taking into account a completely independent test set. Finally, a performance index was evaluated for tbe test emitter models studied. Emitter data with Iow reliability were removed from the processo Performance indexes over 80{\%} were obtained for the remaining test emitters.",
author = "Giuseppe Provenzano and Guillermo Palau-Salvador and {\'A}lvaro Royuela and Pau Mart{\'i}",
year = "2010",
language = "English",
volume = "136",
pages = "11--22",
journal = "Journal of Irrigation and Drainage Engineering - ASCE",
issn = "0733-9437",
publisher = "American Society of Civil Engineers (ASCE)",

}

TY - JOUR

T1 - Integrated emitter local loss prediction using artificial neural networks.

AU - Provenzano, Giuseppe

AU - Palau-Salvador, Guillermo

AU - Royuela, Álvaro

AU - Martí, Pau

PY - 2010

Y1 - 2010

N2 - This paper describes an application of artificiai neural networks (ANNs) to the prediction of Iocai Iosses from integrated emitters. First, the optimum input-output combination was determined. Then, the mapping capability of ANNs and regression models was compared. Afterwards, a five-input ANN model, which considers pipe and emitter internai diameter, emitter length, emitter spacing, and pipe discharge, was used to develop a local losses predicting tool which was obtained from different training strategies while taking into account a completely independent test set. Finally, a performance index was evaluated for tbe test emitter models studied. Emitter data with Iow reliability were removed from the processo Performance indexes over 80% were obtained for the remaining test emitters.

AB - This paper describes an application of artificiai neural networks (ANNs) to the prediction of Iocai Iosses from integrated emitters. First, the optimum input-output combination was determined. Then, the mapping capability of ANNs and regression models was compared. Afterwards, a five-input ANN model, which considers pipe and emitter internai diameter, emitter length, emitter spacing, and pipe discharge, was used to develop a local losses predicting tool which was obtained from different training strategies while taking into account a completely independent test set. Finally, a performance index was evaluated for tbe test emitter models studied. Emitter data with Iow reliability were removed from the processo Performance indexes over 80% were obtained for the remaining test emitters.

UR - http://hdl.handle.net/10447/53818

M3 - Article

VL - 136

SP - 11

EP - 22

JO - Journal of Irrigation and Drainage Engineering - ASCE

JF - Journal of Irrigation and Drainage Engineering - ASCE

SN - 0733-9437

ER -