This paper describes an application of artificiai neural networks (ANNs) to the prediction of Iocai Iosses from integratedemitters. First, the optimum input-output combination was determined. Then, the mapping capability of ANNs and regression models wascompared. Afterwards, a five-input ANN model, which considers pipe and emitter internai diameter, emitter length, emitter spacing, andpipe discharge, was used to develop a local losses predicting tool which was obtained from different training strategies while taking intoaccount a completely independent test set. Finally, a performance index was evaluated for tbe test emitter models studied. Emitter datawith Iow reliability were removed from the processo Performance indexes over 80% were obtained for the remaining test emitters.
|Numero di pagine||12|
|Rivista||JOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING|
|Stato di pubblicazione||Published - 2010|
All Science Journal Classification (ASJC) codes
- Civil and Structural Engineering
- Water Science and Technology
- Agricultural and Biological Sciences (miscellaneous)
Provenzano, G., Royuela, Á., Martí, P., & Palau-Salvador, G. (2010). Integrated emitter local loss prediction using artificial neural networks. JOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING, 136, 11-22.