Analysis of wave transmission behind low-crested breakwaters using neural networks

Panizzo, A.; Briganti, Riccardo

doi:10.1016/j.coastaleng.2007.01.001

Cited by 54 publications

(37 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, an additional geometric parameter has been introduced: the average unit size D representative of the structure elements, which has proved to be relevant in the prediction of K r and K t (Panizzo and Briganti, 2007;Formentin and Zanuttigh, 2013;Zanuttigh et al, 2013). Therefore, the complete database, in its final layout, consists of 13 hydraulic parameters, 18 structural parameters and 3 general parameters (the reliability and complexity factors and the identify name of the test).…”

Section: The Databasementioning

confidence: 99%

“…2):  for q, a total amount of 11,825 tests are available; these data have been collected from: the CLASH database (Van der Meer et al, 2009), which consists of more than 10,000 irregular wave overtopping tests and includes dikes, rubble mound breakwaters, berm breakwaters, caisson structures and combinations with complicated geometries; reports from LWI (Oumeraci et al, 2001(Oumeraci et al, , 2004(Oumeraci et al, and 2007; additional data on smooth steep slopes (Victor, 2012).  for K r , 7,413 data are available, mainly derived from the extended wave reflection database , which collects more than 5,700 data, including the original wave reflection database based on CLASH database (Zanuttigh and Van der Meer, 2008) and additional data on seawalls (Oumeraci et al, 2001(Oumeraci et al, , 2004(Oumeraci et al, and 2007, steep slopes (Victor 2012) and berm breakwaters (Lykke Andersen, 2006);  for K t , additional data structures with berms (Lissev, 1993) have been combined with the DELOS database on low crested breakwaters (Van der Meer et al, 2005;Panizzo and Briganti 2007), which consists of more than 3,000 data, including rubble mound structures, aquareefs, rubble mounds with different kind of armour units and smooth slopes, for a total amount of 3,366 tests. The diagrams in Figure 2 represent the distribution of the data included within each of the three datasets, in order to illustrate the different kind of structures and wave conditions available for each output parameter.…”

Section: The Databasementioning

confidence: 99%

“…The common methodology (Van Gent, 2007;Panizzo and Briganti, 2007;Verhaeghe, 2005) to establish the optimal number of hidden neurons by testing the performance of the ANN as a function of the progressive increase of the number of the hidden neurons has been here adopted. Since the ANN is supposed to predict K r , K t and q, all the applications have been taken into account, and the optimal number has been finally established as the most suitable for all the outputs.…”

Section: The Number Of Hidden Neuronsmentioning

confidence: 99%

“…After and during CLASH (2004) other ANNs have been developed. Specific ANNs were developed for the estimation of the wave overtopping discharge (Verhaeghe et al, 2008), of the wave transmission coefficient (Van Oosten and Peixó Marco, 2005;Panizzo and Briganti, 2007) and of the wave reflection coefficient .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Advances in Modelling Wave-Structure Interaction Through Artificial Neural Networks

Zanuttigh¹,

Formentin²,

Meer³

2014

Int. Conf. Coastal. Eng.

View full text Add to dashboard Cite

This contribution describes a new Artificial Neural Network (ANN) able to predict at once the main parameters representative of the wave-structure interaction processes, i.e. the wave overtopping discharge, the wave transmission coefficient and the wave reflection coefficient. The development of this ANN started with the preparation of a new extended and homogeneous database (derived from CLASH database) which collects all the available tests including at least one of the three parameters, for a total amount of 16,165 data. Some of the existing ANNs were compared and improved, leading to the selection of a final ANN, whose architecture was optimized through an in-depth sensitivity analysis to the learning and training ANN features. The new ANN here proposed provides accurate predictions for all the three parameters, resulting in a tool that can be efficiently used for design purposes. Keywords: artificial neural network, database, wave overtopping, wave reflection, wave transmission INTRODUCTIONThe design of coastal and harbour structures requires a systematic analysis of all the processes of wave-structure interaction, which takes into account the combined effects of wave overtopping, wave transmission and wave reflection. Indeed, all these phenomena should be considered as different outcomes of the same physical process, and therefore should be investigated contemporarily. However, based on the traditional approach most of the existing formulae are targeted to represent just one process and are fitted on specific (more or less wide) databases, addressing usually one or few structure types and having therefore a specific (more or less narrow) validity field.The development and/or use of an Artificial Neural Network (ANN) is therefore particularly recommended in case of complicated structure geometries and variable wave conditions. This kind of predictive method requires however a homogeneous and "wide-enough" database: the number of data should be sufficient for training the ANN based on a number of ANN parameters and including a sufficiently wide number of data for all range of possible output values. There are specific cases that also an ANN cannot deal with, such as very complex walls, perforated caissons and double promenades, see for details EurOtop (2007) and specifically the methodology released within the PC-OVERTOPPING calculator (http://www.overtopping-manual.com/calculation_tool.html).One of the most successful ANNs is the method available from CLASH (2004) and EurOtop (2007) for wave overtopping, which was specifically developed to predict the overtopping discharge for a wide range of coastal structures, including complex geometries (Van Gent et al., 2007). Each of these ANNs actually proved to be able to overcome some of the limits imposed by the traditional empirical formulae, but they are still restricted to reproduce only one of the processes involved in the wave-structure interaction. Nevertheless, the assumption that all the processes are physically correlated implies that a unique set of phys...

show abstract

Section: The Databasementioning

confidence: 99%

Section: The Databasementioning

confidence: 99%

Section: The Number Of Hidden Neuronsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Advances in Modelling Wave-Structure Interaction Through Artificial Neural Networks

Zanuttigh¹,

Formentin²,

Meer³

2014

Int. Conf. Coastal. Eng.

View full text Add to dashboard Cite

show abstract

“…NN models have been widely used to solve problems related to coastal structures (e.g. Mase et al, 1995;Van Gent and Van den Boogaard, 1998;Deo et al, 2002;Medina, 1999;Medina et al, 2002;Panizzo et al, 2003;Kim and Park, 2005;Panizzo and Briganti, 2007;Van Gent et al, 2007;Garrido and Medina, 2012).…”

Section: Iv5 Influence Of the Placement Technique On Cube Armor Stamentioning

confidence: 99%

Mound Breakwater Design in Depth-Limited Breaking Wave Conditions

Gamboa¹,

Piedad²

View full text Add to dashboard Cite

i Agradecimientos Esta tesis doctoral es el fruto de varios años de trabajo, pero su culminación no habría sido posible sin el apoyo y la ayuda de todas aquellas personas importantes que me rodean.A mi padre, por su dedicación y precocupación por mí. Porque sin él, probablemente no estaría escribiendo estas líneas.A mi madre, por su apoyo incondicional, su alegría y su capacidad de ponerse en el lugar del otro. Gracias por estar siempre a mi lado.A mis hermanos, Patricia y Pepe, a los que quiero con locura aunque siempre estemos de 'peleillas'.A mis amigos, porque a pesar de la distancia que nos separa, sois mi segunda familia.A mis compañeros del LPC y departamento, Ainoha, Gloria, Quique, Vicente, Guille, Tomás, César, Pepe, Ana, Esther, Jose Alberto, Joaquín, Miguel…por la ayuda prestada.A Jorge, por todo. Por sus ánimos, su confianza, su paciencia y su ayuda. Porque siempre has estado ahí sin esperar nada a cambio.A mi director de tesis, Josep, quien me ha transmitido su pasión por la ingeniería marítima. Gracias por haberme ofrecido la posibilidad de trabajar contigo, por la ayuda, la confianza y la disponibilidad mostrada todos estos años.Al Ministerio de Educación, Cultura y Deporte, por la financiación brindada a través del programa de Formación de Profesorado Universitario (FPU 13/01872) para la realización de esta tesis doctoral.Al Ministerio de Economía y Competitividad, por la financiación del proyecto ESCOLIF (BIA2012-33967).A Debra Westall, por revisar este documento.iii Resumen El manto principal de los diques en talud suele estar formado por escollera natural o elementos prefabricados de hormigón; su función es resistir la acción del oleaje. Una revisión del estado del arte pone de manifiesto que son numerosas las fórmulas existentes para el diseño de mantos derivadas de ensayos físicos a escala reducida con oleaje sin rotura por fondo. Sin embargo, la mayoría de diques en talud se construyen en la zona de rompientes con oleaje limitado por fondo, donde las ecuaciones de diseño habituales no son del todo válidas. En esta tesis doctoral se analiza la estabilidad hidráulica de mantos bicapa de escollera, a partir de ensayos a escala reducida con pendiente de fondo m=1/50. En base a los resultados obtenidos de los ensayos físicos, se propone una nueva relación potencial para el diseño de mantos de escollera en condiciones de oleaje limitado por fondo, válida para taludes con cotα=1.5, números de estabilidad 0.98≤Hm0/(ΔDn50)≤2.5, y profundidades relativas a pie de dique de 3.75≤hs/(ΔDn50)≤7.50.Cuando el manto principal está formado por elementos de hormigón, es habitual construir una berma de pie que proporciona apoyo a los elementos del manto y, en su caso, colabora en la protección de la zona inferior del dique contra la socavación. Dicha berma suele construirse con escollera natural y su peso está condicionado al de los elementos del manto en el caso de no haber rotura por fondo. El peso de los elementos de la berma de pie suele ser un orden de magnitud inferior al peso de las unidades del manto; ...

show abstract

Artificial Neural Networks

Hajian

Styles

2018

Application of Soft Computing and Intelligent Methods in Geophysics

View full text Add to dashboard Cite

Analysis of wave transmission behind low-crested breakwaters using neural networks

Cited by 54 publications

References 7 publications

Advances in Modelling Wave-Structure Interaction Through Artificial Neural Networks

Advances in Modelling Wave-Structure Interaction Through Artificial Neural Networks

Mound Breakwater Design in Depth-Limited Breaking Wave Conditions

Artificial Neural Networks

Contact Info

Product

Resources

About